NetoPedro / Universal-Adversarial-Perturbations-PytorchLinks
Implementation of https://arxiv.org/abs/1610.08401 for the CS-E4070 - Special Course in Machine Learning and Data Science: Advanced Topics in Deep Learning course at Aalto University, Finland.
☆64Updated 5 years ago
Alternatives and similar repositories for Universal-Adversarial-Perturbations-Pytorch
Users that are interested in Universal-Adversarial-Perturbations-Pytorch are comparing it to the libraries listed below
Sorting:
- Enhancing the Transferability of Adversarial Attacks through Variance Tuning☆89Updated last year
- Code for "Adversarial Camouflage: Hiding Physical World Attacks with Natural Styles" (CVPR 2020)☆94Updated 2 years ago
- A PyTorch implementation of universal adversarial perturbation (UAP) which is more easy to understand and implement.☆54Updated 3 years ago
- ☆71Updated 4 years ago
- Patch-wise iterative attack (accepted by ECCV 2020) to improve the transferability of adversarial examples.☆93Updated 3 years ago
- code for "Feature Importance-aware Transferable Adversarial Attacks"☆85Updated 3 years ago
- Codes for ICLR 2020 paper "Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets"☆70Updated 4 years ago
- ☆53Updated 3 years ago
- Codes for CVPR2020 paper "Towards Transferable Targeted Attack".☆15Updated 3 years ago
- Simple yet effective targeted transferable attack (NeurIPS 2021)☆51Updated 2 years ago
- Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)☆117Updated 3 years ago
- Code for "Adversarial attack by dropping information." (ICCV 2021)☆78Updated 3 years ago
- Adversarial Robustness, White-box, Adversarial Attack☆51Updated 3 years ago
- Beyond imagenet attack (accepted by ICLR 2022) towards crafting adversarial examples for black-box domains.☆60Updated 3 years ago
- This is PyTorch Implementation of Universal Adversarial Perturbation (https://arxiv.org/abs/1610.08401)