Abstract
The ongoing deprecation of third-party cookies by web browser vendors has sparked the proposal of alternative methods to support more privacy-preserving personalized advertising on web browsers and applications. The Topics API is being proposed by Google to provide third-parties with "coarse-grained advertising topics that the page visitor might currently be interested in". In this paper, we analyze the re-identification risks for individual Internet users and the utility provided to advertising companies by the Topics API, i.e. learning the most popular topics and distinguishing between real and random topics. We provide theoretical results dependent only on the API parameters that can be readily applied to evaluate the privacy and utility implications of future API updates, including novel general upper-bounds that account for adversaries with access to unknown, arbitrary side information, the value of the differential privacy parameter $\epsilon$, and experimental results on real-world data that validate our theoretical model.
Keyword: privacy
Factual Dialogue Summarization via Learning from Large Language Models
Authors: Rongxin Zhu, Jey Han Lau, Jianzhong Qi
Subjects: Subjects:
Computation and Language (cs.CL)
Abstract
Factual consistency is an important quality in dialogue summarization. Large language model (LLM)-based automatic text summarization models generate more factually consistent summaries compared to those by smaller pretrained language models, but they face deployment challenges in real-world applications due to privacy or resource constraints. In this paper, we investigate the use of symbolic knowledge distillation to improve the factual consistency of smaller pretrained models for dialogue summarization. We employ zero-shot learning to extract symbolic knowledge from LLMs, generating both factually consistent (positive) and inconsistent (negative) summaries. We then apply two contrastive learning objectives on these summaries to enhance smaller summarization models. Experiments with BART, PEGASUS, and Flan-T5 indicate that our approach surpasses strong baselines that rely on complex data augmentation strategies. Our approach achieves better factual consistency while maintaining coherence, fluency, and relevance, as confirmed by various automatic evaluation metrics. We also provide access to the data and code to facilitate future research.
An Exploratory Mixed-Methods Study on General Data Protection Regulation (GDPR) Compliance in Open-Source Software
Authors: Lucas Franke, Huayu Liang, Sahar Farzanehpour, Aaron Brantly, James C. Davis, Chris Brown
Abstract
Background: Governments worldwide are considering data privacy regulations. These laws, e.g. the European Union's General Data Protection Regulation (GDPR), require software developers to meet privacy-related requirements when interacting with users' data. Prior research describes the impact of such laws on software development, but only for commercial software. Open-source software is commonly integrated into regulated software, and thus must be engineered or adapted for compliance. We do not know how such laws impact open-source software development. Aims: To understand how data privacy laws affect open-source software development. We studied the European Union's GDPR, the most prominent such law. We investigated how GDPR compliance activities influence OSS developer activity (RQ1), how OSS developers perceive fulfilling GDPR requirements (RQ2), the most challenging GDPR requirements to implement (RQ3), and how OSS developers assess GDPR compliance (RQ4). Method: We distributed an online survey to explore perceptions of GDPR implementations from open-source developers (N=56). We further conducted a repository mining study to analyze development metrics on pull requests (N=31462) submitted to open-source GitHub repositories. Results: GDPR policies complicate open-source development processes and introduce challenges for developers, primarily regarding the management of users' data, implementation costs and time, and assessments of compliance. Moreover, we observed negative perceptions of GDPR from open-source developers and significant increases in development activity, in particular metrics related to coding and reviewing activity, on GitHub pull requests related to GDPR compliance. Conclusions: Our findings motivate policy-related resources and automated tools to support data privacy regulation implementation and compliance efforts in open-source software.
Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data
Abstract
Retrieval-augmented generation (RAG) enhances the outputs of language models by integrating relevant information retrieved from external knowledge sources. However, when the retrieval process involves private data, RAG systems may face severe privacy risks, potentially leading to the leakage of sensitive information. To address this issue, we propose using synthetic data as a privacy-preserving alternative for the retrieval data. We propose SAGE, a novel two-stage synthetic data generation paradigm. In the stage-1, we employ an attribute-based extraction and generation approach to preserve key contextual information from the original data. In the stage-2, we further enhance the privacy properties of the synthetic data through an agent-based iterative refinement process. Extensive experiments demonstrate that using our synthetic data as the retrieval context achieves comparable performance to using the original data while substantially reducing privacy risks. Our work takes the first step towards investigating the possibility of generating high-utility and privacy-preserving synthetic data for RAG, opening up new opportunities for the safe application of RAG systems in various domains.
Older and Wiser: The Marriage of Device Aging and Intellectual Property Protection of Deep Neural Networks
Authors: Ning Lin, Shaocong Wang, Yue Zhang, Yangu He, Kwunhang Wong, Arindam Basu, Dashan Shang, Xiaoming Chen, Zhongrui Wang
Subjects: Subjects:
Cryptography and Security (cs.CR); Hardware Architecture (cs.AR)
Abstract
Deep neural networks (DNNs), such as the widely-used GPT-3 with billions of parameters, are often kept secret due to high training costs and privacy concerns surrounding the data used to train them. Previous approaches to securing DNNs typically require expensive circuit redesign, resulting in additional overheads such as increased area, energy consumption, and latency. To address these issues, we propose a novel hardware-software co-design approach for DNN intellectual property (IP) protection that capitalizes on the inherent aging characteristics of circuits and a novel differential orientation fine-tuning (DOFT) to ensure effective protection. Hardware-wise, we employ random aging to produce authorized chips. This process circumvents the need for chip redesign, thereby eliminating any additional hardware overhead during the inference procedure of DNNs. Moreover, the authorized chips demonstrate a considerable disparity in DNN inference performance when compared to unauthorized chips. Software-wise, we propose a novel DOFT, which allows pre-trained DNNs to maintain their original accuracy on authorized chips with minimal fine-tuning, while the model's performance on unauthorized chips is reduced to random guessing. Extensive experiments on various models, including MLP, VGG, ResNet, Mixer, and SwinTransformer, with lightweight binary and practical multi-bit weights demonstrate that the proposed method achieves effective IP protection, with only 10\% accuracy on unauthorized chips, while preserving nearly the original accuracy on authorized ones.
Safely Learning with Private Data: A Federated Learning Framework for Large Language Model
Abstract
Private data, being larger and quality-higher than public data, can greatly improve large language models (LLM). However, due to privacy concerns, this data is often dispersed in multiple silos, making its secure utilization for LLM training a challenge. Federated learning (FL) is an ideal solution for training models with distributed private data, but traditional frameworks like FedAvg are unsuitable for LLM due to their high computational demands on clients. An alternative, split learning, offloads most training parameters to the server while training embedding and output layers locally, making it more suitable for LLM. Nonetheless, it faces significant challenges in security and efficiency. Firstly, the gradients of embeddings are prone to attacks, leading to potential reverse engineering of private data. Furthermore, the server's limitation of handle only one client's training request at a time hinders parallel training, severely impacting training efficiency. In this paper, we propose a Federated Learning framework for LLM, named FL-GLM, which prevents data leakage caused by both server-side and peer-client attacks while improving training efficiency. Specifically, we first place the input block and output block on local client to prevent embedding gradient attacks from server. Secondly, we employ key-encryption during client-server communication to prevent reverse engineering attacks from peer-clients. Lastly, we employ optimization methods like client-batching or server-hierarchical, adopting different acceleration methods based on the actual computational capabilities of the server. Experimental results on NLU and generation tasks demonstrate that FL-GLM achieves comparable metrics to centralized chatGLM model, validating the effectiveness of our federated learning framework.
GiusBERTo: A Legal Language Model for Personal Data De-identification in Italian Court of Auditors Decisions
Abstract
Recent advances in Natural Language Processing have demonstrated the effectiveness of pretrained language models like BERT for a variety of downstream tasks. We present GiusBERTo, the first BERT-based model specialized for anonymizing personal data in Italian legal documents. GiusBERTo is trained on a large dataset of Court of Auditors decisions to recognize entities to anonymize, including names, dates, locations, while retaining contextual relevance. We evaluate GiusBERTo on a held-out test set and achieve 97% token-level accuracy. GiusBERTo provides the Italian legal community with an accurate and tailored BERT model for de-identification, balancing privacy and data protection.
Behaviour Distillation
Authors: Andrei Lupu, Chris Lu, Jarek Liesen, Robert Tjarko Lange, Jakob Foerster
Abstract
Dataset distillation aims to condense large datasets into a small number of synthetic examples that can be used as drop-in replacements when training new models. It has applications to interpretability, neural architecture search, privacy, and continual learning. Despite strong successes in supervised domains, such methods have not yet been extended to reinforcement learning, where the lack of a fixed dataset renders most distillation methods unusable. Filling the gap, we formalize behaviour distillation, a setting that aims to discover and then condense the information required for training an expert policy into a synthetic dataset of state-action pairs, without access to expert data. We then introduce Hallucinating Datasets with Evolution Strategies (HaDES), a method for behaviour distillation that can discover datasets of just four state-action pairs which, under supervised learning, train agents to competitive performance levels in continuous control tasks. We show that these datasets generalize out of distribution to training policies with a wide range of architectures and hyperparameters. We also demonstrate application to a downstream task, namely training multi-task agents in a zero-shot fashion. Beyond behaviour distillation, HaDES provides significant improvements in neuroevolution for RL over previous approaches and achieves SoTA results on one standard supervised dataset distillation task. Finally, we show that visualizing the synthetic datasets can provide human-interpretable task insights.
Delegated-Query Oblivious Transfer and its Practical Applications
Authors: Yvo Desmedt, Aydin Abadi
Subjects: Subjects:
Cryptography and Security (cs.CR)
Abstract
Databases play a pivotal role in the contemporary World Wide Web and the world of cloud computing. Unfortunately, numerous privacy violations have recently garnered attention in the news. To enhance database privacy, we consider Oblivious Transfer (OT), an elegant cryptographic technology. Our observation reveals that existing research in this domain primarily concentrates on theoretical cryptographic applications, overlooking various practical aspects: - OTs assume parties have direct access to databases. Our "1-out-of-2 Delegated-Query OT" enables parties to privately query a database, without direct access. - With the rise of cloud computing, physically separated databases may no longer remain so. Our "1-out-of-2 Delegated-Query Multi-Receiver OT" protects privacy in such evolving scenarios. - Research often ignores the limitations of thin clients, e.g., Internet of Things devices. To address this, we propose a compiler that transforms any 1-out-of-n OT into a thin client version.
Balancing The Perception of Cheating Detection, Privacy and Fairness: A Mixed-Methods Study of Visual Data Obfuscation in Remote Proctoring
Authors: Suvadeep Mukherjee, Verena Distler, Gabriele Lenzini, Pedro Cardoso-Leite
Abstract
Remote proctoring technology, a cheating-preventive measure, often raises privacy and fairness concerns that may affect test-takers' experiences and the validity of test results. Our study explores how selectively obfuscating information in video recordings can protect test-takers' privacy while ensuring effective and fair cheating detection. Interviews with experts (N=9) identified four key video regions indicative of potential cheating behaviors: the test-taker's face, body, background and the presence of individuals in the background. Experts recommended specific obfuscation methods for each region based on privacy significance and cheating behavior frequency, ranging from conventional blurring to advanced methods like replacement with deepfake, 3D avatars and silhouetting. We then conducted a vignette experiment with potential test-takers (N=259, non-experts) to evaluate their perceptions of cheating detection, visual privacy and fairness, using descriptions and examples of still images for each expert-recommended combination of video regions and obfuscation methods. Our results indicate that the effectiveness of obfuscation methods varies by region. Tailoring remote proctoring with region-specific advanced obfuscation methods can improve the perceptions of privacy and fairness compared to the conventional methods, though it may decrease perceived information sufficiency for detecting cheating. However, non-experts preferred conventional blurring for videos they were more willing to share, highlighting a gap between the perceived effectiveness of the advanced obfuscation methods and their practical acceptance. This study contributes to the field of user-centered privacy by suggesting promising directions to address current remote proctoring challenges and guiding future research.
Speech Emotion Recognition under Resource Constraints with Data Distillation
Authors: Yi Chang, Zhao Ren, Zhonghao Zhao, Thanh Tam Nguyen, Kun Qian, Tanja Schultz, Björn W. Schuller
Abstract
Speech emotion recognition (SER) plays a crucial role in human-computer interaction. The emergence of edge devices in the Internet of Things (IoT) presents challenges in constructing intricate deep learning models due to constraints in memory and computational resources. Moreover, emotional speech data often contains private information, raising concerns about privacy leakage during the deployment of SER models. To address these challenges, we propose a data distillation framework to facilitate efficient development of SER models in IoT applications using a synthesised, smaller, and distilled dataset. Our experiments demonstrate that the distilled dataset can be effectively utilised to train SER models with fixed initialisation, achieving performances comparable to those developed using the original full emotional speech dataset.
Fingerprint Membership and Identity Inference Against Generative Adversarial Networks
Abstract
Generative models are gaining significant attention as potential catalysts for a novel industrial revolution. Since automated sample generation can be useful to solve privacy and data scarcity issues that usually affect learned biometric models, such technologies became widely spread in this field. In this paper, we assess the vulnerabilities of generative machine learning models concerning identity protection by designing and testing an identity inference attack on fingerprint datasets created by means of a generative adversarial network. Experimental results show that the proposed solution proves to be effective under different configurations and easily extendable to other biometric measurements.
Abstract
As Artificial General Intelligence (AGI) becomes increasingly integrated into various facets of human life, ensuring the safety and ethical alignment of such systems is paramount. Previous studies primarily focus on single-modality threats, which may not suffice given the integrated and complex nature of cross-modality interactions. We introduce a novel safety alignment challenge called Safe Inputs but Unsafe Output (SIUO) to evaluate cross-modality safety alignment. Specifically, it considers cases where single modalities are safe independently but could potentially lead to unsafe or unethical outputs when combined. To empirically investigate this problem, we developed the SIUO, a cross-modality benchmark encompassing 9 critical safety domains, such as self-harm, illegal activities, and privacy violations. Our findings reveal substantial safety vulnerabilities in both closed- and open-source LVLMs, such as GPT-4V and LLaVA, underscoring the inadequacy of current models to reliably interpret and respond to complex, real-world scenarios.
PID: Prompt-Independent Data Protection Against Latent Diffusion Models
Authors: Ang Li, Yichuan Mo, Mingjie Li, Yisen Wang
Subjects: Subjects:
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
Abstract
The few-shot fine-tuning of Latent Diffusion Models (LDMs) has enabled them to grasp new concepts from a limited number of images. However, given the vast amount of personal images accessible online, this capability raises critical concerns about civil privacy. While several previous defense methods have been developed to prevent such misuse of LDMs, they typically assume that the textual prompts used by data protectors exactly match those employed by data exploiters. In this paper, we first empirically demonstrate that breaking this assumption, i.e., in cases where discrepancies exist between the textual conditions used by protectors and exploiters, could substantially reduce the effectiveness of these defenses. Furthermore, considering the visual encoder's independence from textual prompts, we delve into the visual encoder and thoroughly investigate how manipulating the visual encoder affects the few-shot fine-tuning process of LDMs. Drawing on these insights, we propose a simple yet effective method called \textbf{Prompt-Independent Defense (PID)} to safeguard privacy against LDMs. We show that PID can act as a strong privacy shield on its own while requiring significantly less computational power. We believe our studies, along with the comprehensive understanding and new defense method, provide a notable advance toward reliable data protection against LDMs.
The Privacy-Utility Trade-off in the Topics API
Authors: Mário S. Alvim, Natasha Fernandes, Annabelle McIver, Gabriel H. Nunes
Subjects: Subjects:
Cryptography and Security (cs.CR)
Abstract
The ongoing deprecation of third-party cookies by web browser vendors has sparked the proposal of alternative methods to support more privacy-preserving personalized advertising on web browsers and applications. The Topics API is being proposed by Google to provide third-parties with "coarse-grained advertising topics that the page visitor might currently be interested in". In this paper, we analyze the re-identification risks for individual Internet users and the utility provided to advertising companies by the Topics API, i.e. learning the most popular topics and distinguishing between real and random topics. We provide theoretical results dependent only on the API parameters that can be readily applied to evaluate the privacy and utility implications of future API updates, including novel general upper-bounds that account for adversaries with access to unknown, arbitrary side information, the value of the differential privacy parameter $\epsilon$, and experimental results on real-world data that validate our theoretical model.
Abstract
Newly diagnosed Type 1 Diabetes (T1D) patients often struggle to obtain effective Blood Glucose (BG) prediction models due to the lack of sufficient BG data from Continuous Glucose Monitoring (CGM), presenting a significant "cold start" problem in patient care. Utilizing population models to address this challenge is a potential solution, but collecting patient data for training population models in a privacy-conscious manner is challenging, especially given that such data is often stored on personal devices. Considering the privacy protection and addressing the "cold start" problem in diabetes care, we propose "GluADFL", blood Glucose prediction by Asynchronous Decentralized Federated Learning. We compared GluADFL with eight baseline methods using four distinct T1D datasets, comprising 298 participants, which demonstrated its superior performance in accurately predicting BG levels for cross-patient analysis. Furthermore, patients' data might be stored and shared across various communication networks in GluADFL, ranging from highly interconnected (e.g., random, performs the best among others) to more structured topologies (e.g., cluster and ring), suitable for various social networks. The asynchronous training framework supports flexible participation. By adjusting the ratios of inactive participants, we found it remains stable if less than 70% are inactive. Our results confirm that GluADFL offers a practical, privacy-preserving solution for BG prediction in T1D, significantly enhancing the quality of diabetes management.
Keyword: machine learning
3D Instance Segmentation Using Deep Learning on RGB-D Indoor Data
Authors: Siddiqui Muhammad Yasir, Amin Muhammad Sadiq, Hyunsik Ahn
Subjects: Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Abstract
3D object recognition is a challenging task for intelligent and robot systems in industrial and home indoor environments. It is critical for such systems to recognize and segment the 3D object instances that they encounter on a frequent basis. The computer vision, graphics, and machine learning fields have all given it a lot of attention. Traditionally, 3D segmentation was done with hand-crafted features and designed approaches that did not achieve acceptable performance and could not be generalized to large-scale data. Deep learning approaches have lately become the preferred method for 3D segmentation challenges by their great success in 2D computer vision. However, the task of instance segmentation is currently less explored. In this paper, we propose a novel approach for efficient 3D instance segmentation using red green blue and depth (RGB-D) data based on deep learning. The 2D region based convolutional neural networks (Mask R-CNN) deep learning model with point based rending module is adapted to integrate with depth information to recognize and segment 3D instances of objects. In order to generate 3D point cloud coordinates (x, y, z), segmented 2D pixels (u, v) of recognized object regions in the RGB image are merged into (u, v) points of the depth image. Moreover, we conducted an experiment and analysis to compare our proposed method from various points of view and distances. The experimentation shows the proposed 3D object recognition and instance segmentation are sufficiently beneficial to support object handling in robotic and intelligent systems.
Modeling & Evaluating the Performance of Convolutional Neural Networks for Classifying Steel Surface Defects
Authors: Nadeem Jabbar Chaudhry, M. Bilal Khan, M. Javaid Iqbal, Siddiqui Muhammad Yasir
Subjects: Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Abstract
Recently, outstanding identification rates in image classification tasks were achieved by convolutional neural networks (CNNs). to use such skills, selective CNNs trained on a dataset of well-known images of metal surface defects captured with an RGB camera. Defects must be detected early to take timely corrective action due to production concerns. For image classification up till now, a model-based method has been utilized, which indicated the predicted reflection characteristics of surface defects in comparison to flaw-free surfaces. The problem of detecting steel surface defects has grown in importance as a result of the vast range of steel applications in end-product sectors such as automobiles, households, construction, etc. The manual processes for detections are time-consuming, labor-intensive, and expensive. Different strategies have been used to automate manual processes, but CNN models have proven to be the most effective rather than image processing and machine learning techniques. By using different CNN models with fine-tuning, easily compare their performance and select the best-performing model for the same kinds of tasks. However, it is important that using different CNN models either from fine tuning can be computationally expensive and time-consuming. Therefore, our study helps the upcoming researchers to choose the CNN without considering the issues of model complexity, performance, and computational resources. In this article, the performance of various CNN models with transfer learning techniques are evaluated. These models were chosen based on their popularity and impact in the field of computer vision research, as well as their performance on benchmark datasets. According to the outcomes, DenseNet201 outperformed the other CNN models and had the greatest detection rate on the NEU dataset, falling in at 98.37 percent.
Physics-informed neural networks for parameter learning of wildfire spreading
Abstract
Wildland fires pose terrifying natural hazards, underscoring the urgent need to develop data-driven and physics-informed digital twins for wildfire prevention, monitoring, intervention, and response. In this direction of research, this work introduces a physics-informed neural network (PiNN) to learn the unknown parameters of an interpretable wildfire spreading model. The considered wildfire spreading model integrates fundamental physical laws articulated by key model parameters, essential for capturing the complex behavior of wildfires. The proposed machine learning approach leverages the theory of artificial neural networks with the physical constraints governing wildfire dynamics, such as the first principles of mass and energy conservation. Training of the PiNN for physics-informed parameter identification is realized using data of the temporal evolution of one- and two-dimensional (plane surface) fire fronts that have been obtained from a high-fidelity simulator of the wildfire spreading model under consideration. The parameter learning results demonstrate the remarkable predictive ability of the proposed PiNN in uncovering the unknown coefficients in both the one- and two-dimensional fire spreading scenarios. Additionally, this methodology exhibits robustness by identifying the same parameters in the presence of noisy data. The proposed framework is envisioned to be incorporated in a physics-informed digital twin for intelligent wildfire management and risk assessment.
A Large Language Model Outperforms Other Computational Approaches to the High-Throughput Phenotyping of Physician Notes
Authors: Syed I. Munzir, Daniel B. Hier, Chelsea Oommen, Michael D. Carrithers
Abstract
High-throughput phenotyping, the automated mapping of patient signs and symptoms to standardized ontology concepts, is essential to gaining value from electronic health records (EHR) in the support of precision medicine. Despite technological advances, high-throughput phenotyping remains a challenge. This study compares three computational approaches to high-throughput phenotyping: a Large Language Model (LLM) incorporating generative AI, a Natural Language Processing (NLP) approach utilizing deep learning for span categorization, and a hybrid approach combining word vectors with machine learning. The approach that implemented GPT-4 (a Large Language Model) demonstrated superior performance, suggesting that Large Language Models are poised to be the preferred method for high-throughput phenotyping of physician notes.
Learning to Cover: Online Learning and Optimization with Irreversible Decisions
Authors: Alexandre Jacquillat, Michael Lingzhi Li
Subjects: Subjects:
Machine Learning (cs.LG); Optimization and Control (math.OC)
Abstract
We define an online learning and optimization problem with irreversible decisions contributing toward a coverage target. At each period, a decision-maker selects facilities to open, receives information on the success of each one, and updates a machine learning model to guide future decisions. The goal is to minimize costs across a finite horizon under a chance constraint reflecting the coverage target. We derive an optimal algorithm and a tight lower bound in an asymptotic regime characterized by a large target number of facilities $m\to\infty$ but a finite horizon $T\in\mathbb{Z}_+$. We find that the regret grows sub-linearly at a rate $\Theta\left(m^{\frac{1}{2}\cdot\frac{1}{1-2^{-T}}}\right)$, thus converging exponentially fast to $\Theta(\sqrt{m})$. We establish the robustness of this result to the learning environment; we also extend it to a more complicated facility location setting in a bipartite facility-customer graph with a target on customer coverage. Throughout, constructive proofs identify a policy featuring limited exploration initially for learning purposes, and fast exploitation later on for optimization purposes once uncertainty gets mitigated. These findings underscore the benefits of limited online learning and optimization, in that even a few rounds can provide significant benefits as compared to a no-learning baseline.
LatentExplainer: Explaining Latent Representations in Deep Generative Models with Multi-modal Foundation Models
Authors: Mengdan Zhu, Raasikh Kanjiani, Jiahui Lu, Andrew Choi, Qirui Ye, Liang Zhao
Subjects: Subjects:
Machine Learning (cs.LG); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
Abstract
Deep generative models like VAEs and diffusion models have advanced various generation tasks by leveraging latent variables to learn data distributions and generate high-quality samples. Despite the field of explainable AI making strides in interpreting machine learning models, understanding latent variables in generative models remains challenging. This paper introduces LatentExplainer, a framework for automatically generating semantically meaningful explanations of latent variables in deep generative models. LatentExplainer tackles three main challenges: inferring the meaning of latent variables, aligning explanations with inductive biases, and handling varying degrees of explainability. By perturbing latent variables and interpreting changes in generated data, the framework provides a systematic approach to understanding and controlling the data generation process, enhancing the transparency and interpretability of deep generative models. We evaluate our proposed method on several real-world and synthetic datasets, and the results demonstrate superior performance in generating high-quality explanations of latent variables.
A review of feature selection strategies utilizing graph data structures and knowledge graphs
Authors: Sisi Shao, Pedro Henrique Ribeiro, Christina Ramirez, Jason H. Moore
Abstract
Feature selection in Knowledge Graphs (KGs) are increasingly utilized in diverse domains, including biomedical research, Natural Language Processing (NLP), and personalized recommendation systems. This paper delves into the methodologies for feature selection within KGs, emphasizing their roles in enhancing machine learning (ML) model efficacy, hypothesis generation, and interpretability. Through this comprehensive review, we aim to catalyze further innovation in feature selection for KGs, paving the way for more insightful, efficient, and interpretable analytical models across various domains. Our exploration reveals the critical importance of scalability, accuracy, and interpretability in feature selection techniques, advocating for the integration of domain knowledge to refine the selection process. We highlight the burgeoning potential of multi-objective optimization and interdisciplinary collaboration in advancing KG feature selection, underscoring the transformative impact of such methodologies on precision medicine, among other fields. The paper concludes by charting future directions, including the development of scalable, dynamic feature selection algorithms and the integration of explainable AI principles to foster transparency and trust in KG-driven models.
Towards Dynamic Resource Allocation and Client Scheduling in Hierarchical Federated Learning: A Two-Phase Deep Reinforcement Learning Approach
Abstract
Federated learning (FL) is a viable technique to train a shared machine learning model without sharing data. Hierarchical FL (HFL) system has yet to be studied regrading its multiple levels of energy, computation, communication, and client scheduling, especially when it comes to clients relying on energy harvesting to power their operations. This paper presents a new two-phase deep deterministic policy gradient (DDPG) framework, referred to as ``TP-DDPG'', to balance online the learning delay and model accuracy of an FL process in an energy harvesting-powered HFL system. The key idea is that we divide optimization decisions into two groups, and employ DDPG to learn one group in the first phase, while interpreting the other group as part of the environment to provide rewards for training the DDPG in the second phase. Specifically, the DDPG learns the selection of participating clients, and their CPU configurations and the transmission powers. A new straggler-aware client association and bandwidth allocation (SCABA) algorithm efficiently optimizes the other decisions and evaluates the reward for the DDPG. Experiments demonstrate that with substantially reduced number of learnable parameters, the TP-DDPG can quickly converge to effective polices that can shorten the training time of HFL by 39.4% compared to its benchmarks, when the required test accuracy of HFL is 0.9.
Brightearth roads: Towards fully automatic road network extraction from satellite imagery
Abstract
The modern road network topology comprises intricately designed structures that introduce complexity when automatically reconstructing road networks. While open resources like OpenStreetMap (OSM) offer road networks with well-defined topology, they may not always be up to date worldwide. In this paper, we propose a fully automated pipeline for extracting road networks from very-high-resolution (VHR) satellite imagery. Our approach directly generates road line-strings that are seamlessly connected and precisely positioned. The process involves three key modules: a CNN-based neural network for road segmentation, a graph optimization algorithm to convert road predictions into vector line-strings, and a machine learning model for classifying road materials. Compared to OSM data, our results demonstrate significant potential for providing the latest road layouts and precise positions of road segments.
Online detection and infographic explanation of spam reviews with data drift adaptation
Authors: Francisco de Arriba-Pérez, Silvia García-Méndez, Fátima Leal, Benedita Malheiro, J. C. Burguillo
Subjects: Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Social and Information Networks (cs.SI)
Abstract
Spam reviews are a pervasive problem on online platforms due to its significant impact on reputation. However, research into spam detection in data streams is scarce. Another concern lies in their need for transparency. Consequently, this paper addresses those problems by proposing an online solution for identifying and explaining spam reviews, incorporating data drift adaptation. It integrates (i) incremental profiling, (ii) data drift detection & adaptation, and (iii) identification of spam reviews employing Machine Learning. The explainable mechanism displays a visual and textual prediction explanation in a dashboard. The best results obtained reached up to 87 % spam F-measure.
GOAL: A Generalist Combinatorial Optimization Agent Learner
Authors: Darko Drakulic, Sofia Michel, Jean-Marc Andreoli
Abstract
Machine Learning-based heuristics have recently shown impressive performance in solving a variety of hard combinatorial optimization problems (COPs). However they generally rely on a separate neural model, specialized and trained for each single problem. Any variation of a problem requires adjustment of its model and re-training from scratch. In this paper, we propose GOAL (for Generalist combinatorial Optimization Agent Learning), a generalist model capable of efficiently solving multiple COPs and which can be fine-tuned to solve new COPs. GOAL consists of a single backbone plus light-weight problem-specific adapters, mostly for input and output processing. The backbone is based on a new form of mixed-attention blocks which allows to handle problems defined on graphs with arbitrary combinations of node, edge and instance-level features. Additionally, problems which involve heterogeneous nodes or edges, such as in multi-partite graphs, are handled through a novel multi-type transformer architecture, where the attention blocks are duplicated to attend only the relevant combination of types while relying on the same shared parameters. We train GOAL on a set of routing, scheduling and classic graph problems and show that it is only slightly inferior to the specialized baselines while being the first multi-task model that solves a variety of COPs. Finally, we showcase the strong transfer learning capacity of GOAL by fine-tuning or learning the adapters for new problems, with only few shots and little data.
A Unified Framework for Input Feature Attribution Analysis
Abstract
Explaining the decision-making process of machine learning models is crucial for ensuring their reliability and fairness. One popular explanation form highlights key input features, such as i) tokens (e.g., Shapley Values and Integrated Gradients), ii) interactions between tokens (e.g., Bivariate Shapley and Attention-based methods), or iii) interactions between spans of the input (e.g., Louvain Span Interactions). However, these explanation types have only been studied in isolation, making it difficult to judge their respective applicability. To bridge this gap, we propose a unified framework that facilitates a direct comparison between highlight and interactive explanations comprised of four diagnostic properties. Through extensive analysis across these three types of input feature explanations--each utilizing three different explanation techniques--across two datasets and two models, we reveal that each explanation type excels in terms of different diagnostic properties. In our experiments, highlight explanations are the most faithful to a model's prediction, and interactive explanations provide better utility for learning to simulate a model's predictions. These insights further highlight the need for future research to develop combined methods that enhance all diagnostic properties.
This actually looks like that: Proto-BagNets for local and global interpretability-by-design
Authors: Kerol Djoumessi, Bubacarr Bah, Laura Kühlewein, Philipp Berens, Lisa Koch
Abstract
Interpretability is a key requirement for the use of machine learning models in high-stakes applications, including medical diagnosis. Explaining black-box models mostly relies on post-hoc methods that do not faithfully reflect the model's behavior. As a remedy, prototype-based networks have been proposed, but their interpretability is limited as they have been shown to provide coarse, unreliable, and imprecise this http URL this work, we introduce Proto-BagNets, an interpretable-by-design prototype-based model that combines the advantages of bag-of-local feature models and prototype learning to provide meaningful, coherent, and relevant prototypical parts needed for accurate and interpretable image classification tasks. We evaluated the Proto-BagNet for drusen detection on publicly available retinal OCT data. The Proto-BagNet performed comparably to the state-of-the-art interpretable and non-interpretable models while providing faithful, accurate, and clinically meaningful local and global explanations. The code is available at this https URL.
Machine Learning Techniques in Automatic Music Transcription: A Systematic Survey
Authors: Fatemeh Jamshidi, Gary Pike, Amit Das, Richard Chapman
Abstract
In the domain of Music Information Retrieval (MIR), Automatic Music Transcription (AMT) emerges as a central challenge, aiming to convert audio signals into symbolic notations like musical notes or sheet music. This systematic review accentuates the pivotal role of AMT in music signal analysis, emphasizing its importance due to the intricate and overlapping spectral structure of musical harmonies. Through a thorough examination of existing machine learning techniques utilized in AMT, we explore the progress and constraints of current models and methodologies. Despite notable advancements, AMT systems have yet to match the accuracy of human experts, largely due to the complexities of musical harmonies and the need for nuanced interpretation. This review critically evaluates both fully automatic and semi-automatic AMT systems, emphasizing the importance of minimal user intervention and examining various methodologies proposed to date. By addressing the limitations of prior techniques and suggesting avenues for improvement, our objective is to steer future research towards fully automated AMT systems capable of accurately and efficiently translating intricate audio signals into precise symbolic representations. This study not only synthesizes the latest advancements but also lays out a road-map for overcoming existing challenges in AMT, providing valuable insights for researchers aiming to narrow the gap between current systems and human-level transcription accuracy.
Fingerprint Membership and Identity Inference Against Generative Adversarial Networks
Abstract
Generative models are gaining significant attention as potential catalysts for a novel industrial revolution. Since automated sample generation can be useful to solve privacy and data scarcity issues that usually affect learned biometric models, such technologies became widely spread in this field. In this paper, we assess the vulnerabilities of generative machine learning models concerning identity protection by designing and testing an identity inference attack on fingerprint datasets created by means of a generative adversarial network. Experimental results show that the proposed solution proves to be effective under different configurations and easily extendable to other biometric measurements.
Towards Robust Training Datasets for Machine Learning with Ontologies: A Case Study for Emergency Road Vehicle Detection
Abstract
Countless domains rely on Machine Learning (ML) models, including safety-critical domains, such as autonomous driving, which this paper focuses on. While the black box nature of ML is simply a nuisance in some domains, in safety-critical domains, this makes ML models difficult to trust. To fully utilize ML models in safety-critical domains, it would be beneficial to have a method to improve trust in model robustness and accuracy without human experts checking each decision. This research proposes a method to increase trust in ML models used in safety-critical domains by ensuring the robustness and completeness of the model's training dataset. Because ML models embody what they are trained with, ensuring the completeness of training datasets can help to increase the trust in the training of ML models. To this end, this paper proposes the use of a domain ontology and an image quality characteristic ontology to validate the domain completeness and image quality robustness of a training dataset. This research also presents an experiment as a proof of concept for this method, where ontologies are built for the emergency road vehicle domain.
FT-AED: Benchmark Dataset for Early Freeway Traffic Anomalous Event Detection
Authors: Austin Coursey, Junyi Ji, Marcos Quinones-Grueiro, William Barbour, Yuhang Zhang, Tyler Derr, Gautam Biswas
Abstract
Early and accurate detection of anomalous events on the freeway, such as accidents, can improve emergency response and clearance. However, existing delays and errors in event identification and reporting make it a difficult problem to solve. Current large-scale freeway traffic datasets are not designed for anomaly detection and ignore these challenges. In this paper, we introduce the first large-scale lane-level freeway traffic dataset for anomaly detection. Our dataset consists of a month of weekday radar detection sensor data collected in 4 lanes along an 18-mile stretch of Interstate 24 heading toward Nashville, TN, comprising over 3.7 million sensor measurements. We also collect official crash reports from the Nashville Traffic Management Center and manually label all other potential anomalies in the dataset. To show the potential for our dataset to be used in future machine learning and traffic research, we benchmark numerous deep learning anomaly detection models on our dataset. We find that unsupervised graph neural network autoencoders are a promising solution for this problem and that ignoring spatial relationships leads to decreased performance. We demonstrate that our methods can reduce reporting delays by over 10 minutes on average while detecting 75% of crashes. Our dataset and all preprocessing code needed to get started are publicly released at this https URL to facilitate future research.
GenoTEX: A Benchmark for Evaluating LLM-Based Exploration of Gene Expression Data in Alignment with Bioinformaticians
Abstract
Recent advancements in machine learning have significantly improved the identification of disease-associated genes from gene expression datasets. However, these processes often require extensive expertise and manual effort, limiting their scalability. Large Language Model (LLM)-based agents have shown promise in automating these tasks due to their increasing problem-solving abilities. To support the evaluation and development of such methods, we introduce GenoTEX, a benchmark dataset for the automatic exploration of gene expression data, involving the tasks of dataset selection, preprocessing, and statistical analysis. GenoTEX provides annotated code and results for solving a wide range of gene identification problems, in a full analysis pipeline that follows the standard of computational genomics. These annotations are curated by human bioinformaticians who carefully analyze the datasets to ensure accuracy and reliability. To provide baselines for these tasks, we present GenoAgents, a team of LLM-based agents designed with context-aware planning, iterative correction, and domain expert consultation to collaboratively explore gene datasets. Our experiments with GenoAgents demonstrate the potential of LLM-based approaches in genomics data analysis, while error analysis highlights the challenges and areas for future improvement. We propose GenoTEX as a promising resource for benchmarking and enhancing AI-driven methods for genomics data analysis. We make our benchmark publicly available at \url{this https URL}.
Keyword: differential privacy
The Privacy-Utility Trade-off in the Topics API
Keyword: privacy
Factual Dialogue Summarization via Learning from Large Language Models
An Exploratory Mixed-Methods Study on General Data Protection Regulation (GDPR) Compliance in Open-Source Software
Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data
Older and Wiser: The Marriage of Device Aging and Intellectual Property Protection of Deep Neural Networks
Safely Learning with Private Data: A Federated Learning Framework for Large Language Model
GiusBERTo: A Legal Language Model for Personal Data De-identification in Italian Court of Auditors Decisions
Behaviour Distillation
Delegated-Query Oblivious Transfer and its Practical Applications
Balancing The Perception of Cheating Detection, Privacy and Fairness: A Mixed-Methods Study of Visual Data Obfuscation in Remote Proctoring
Speech Emotion Recognition under Resource Constraints with Data Distillation
Fingerprint Membership and Identity Inference Against Generative Adversarial Networks
Cross-Modality Safety Alignment
PID: Prompt-Independent Data Protection Against Latent Diffusion Models
The Privacy-Utility Trade-off in the Topics API
Privacy Preserved Blood Glucose Level Cross-Prediction: An Asynchronous Decentralized Federated Learning Approach
Keyword: machine learning
3D Instance Segmentation Using Deep Learning on RGB-D Indoor Data
Modeling & Evaluating the Performance of Convolutional Neural Networks for Classifying Steel Surface Defects
Physics-informed neural networks for parameter learning of wildfire spreading
A Large Language Model Outperforms Other Computational Approaches to the High-Throughput Phenotyping of Physician Notes
Learning to Cover: Online Learning and Optimization with Irreversible Decisions
LatentExplainer: Explaining Latent Representations in Deep Generative Models with Multi-modal Foundation Models
A review of feature selection strategies utilizing graph data structures and knowledge graphs
Towards Dynamic Resource Allocation and Client Scheduling in Hierarchical Federated Learning: A Two-Phase Deep Reinforcement Learning Approach
Brightearth roads: Towards fully automatic road network extraction from satellite imagery
Online detection and infographic explanation of spam reviews with data drift adaptation
GOAL: A Generalist Combinatorial Optimization Agent Learner
A Unified Framework for Input Feature Attribution Analysis
This actually looks like that: Proto-BagNets for local and global interpretability-by-design
Machine Learning Techniques in Automatic Music Transcription: A Systematic Survey
Fingerprint Membership and Identity Inference Against Generative Adversarial Networks
Towards Robust Training Datasets for Machine Learning with Ontologies: A Case Study for Emergency Road Vehicle Detection
FT-AED: Benchmark Dataset for Early Freeway Traffic Anomalous Event Detection
GenoTEX: A Benchmark for Evaluating LLM-Based Exploration of Gene Expression Data in Alignment with Bioinformaticians