-
**Submitting author:** @nic-barbara (Nicholas Barbara)
**Repository:** https://github.com/acfr/RobustNeuralNetworks.jl
**Branch with paper.md** (empty if default branch): paper
**Version:** v0.3.2
**E…
-
What prevents you from directly check the response for the input in the first place, if the response is safe, then return this to the user, if not, then just reject to answer? Why bother to use this e…
-
Hi
Can you please verify the adversarial patch size used for evaluating ImageNet trained models (b=19) in Table 1 of paper:
1% pixels: 23x23
2% pixels: 32x32
3% pixels: 39x39
-
**Request to add a new attack recipe**:
Zhang, Chong, Jieyu Zhao, Huan Zhang, Kai-Wei Chang and Cho-Jui Hsieh. “_Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluatio…
-
Hello @jiachens, @akshaymehra24, @hendrycks, and other authors of the paper,
The current repository does not have any organised codebase for the ECCV'22 paper "A Spectral View of Randomized Smoothing…
-
The current Randomized Smoothing is a generic method, that we use the averaged logits of samples from Gaussian distribution as the prediction result. However, according to [Certified Adversarial Robus…
-
Hello,
Thanks for your efforts in benchmarking the existing verification methods.
I have a question regarding the results in Table 3 of Appendix in your paper https://arxiv.org/pdf/2009.04131.pdf…
-
Hello huanzhang,
I saw in Built-in Models, there is a brelu" (7-layer CNN with Bounded ReLU) option. but brelu is missing inside the train network codes(train_models.py; train_2layer.py; train_nlay…
-
Hi!
Your work is so interesting! Thank you!
But is there the code written by pytorch?
-
| Keywords | References | link |
|-------------------------------|-------------------------------|---------------------------------|
| D…