-
On at least two counts the paper choses l_infinity distortion bounds that are not well motivated.
- Throughout the paper the report studies a CIFAR-10 distortion of eps=0.1 and eps=0.2. This val…
-
We currently have 3 detectors. In this issue I will investigate some possible new additions.
Top candidates:
- [ ] [Neural Cleanse](https://www.semanticscholar.org/paper/Neural-Cleanse%3A-Identif…
-
## URL(s) with the issue:
https://www.tensorflow.org/api_docs/python/tf/image/resize
## Description of issue:
TensorFlow is vulnerable to image-scaling attacks if specific scaling algorithms an…
EQuiw updated
7 months ago
-
Hi xuanqing, I just read you paper "Towards Robust Neural Networks via Random Self-ensemble" and I do think RSE is a brilliant idea.
I have one simple question about your experiement setting. You men…
-
when i run the command:
python defense.py --model UNet --model_path "path" --reformer autoencoder1 --detector autoencoder1 \
--reformer_path checkpoints/autoencoder1.pth --detector_path checkpoints/…
-
Hi~ Thanks for sharing this great work! I have one question about the experimental details while conducting nettack attack.
It looks that nettack[1] in deeprobust can only perturb the graph strucu…
-
Hello, I'm just read the paper, and it's quite brilliant idea to apply a input transformation defence to circumvent existing advanced gradient attack without retrain model or degrading performance.
…
-
There is a claim that "causing a benign program to be misclassified as malware may be uninteresting." It's risky to eliminate threats based on the author's understanding of attacker motivations. I s…
-
Exposing Previously Undetectable Faults in Deep Neural Networks
Isaac Dunn, Hadrien Pouget, Daniel Kroening, Tom Melham
DeepCrime: Mutation Testing of Deep Learning Systems based on Real Faults
N…
-
Thesis defense target: 21 June 2024. Survey target: end of July 2023.
Would like to have a fresh master thesis topic, not incremental improvement of other thesis work.
Starting roughly Q1 2023 or su…