qilong-zhang / Patch-wise-iterative-attack
Patch-wise iterative attack (accepted by ECCV 2020) to improve the transferability of adversarial examples.
☆90Updated 2 years ago
Alternatives and similar repositories for Patch-wise-iterative-attack:
Users that are interested in Patch-wise-iterative-attack are comparing it to the libraries listed below
- The extension of "Patch-wise Attack for Fooling Deep Neural Network (ECCV2020)", and we aim to boost the success rates of targeted attack…☆27Updated 2 years ago
- A PyTorch implementation of universal adversarial perturbation (UAP) which is more easy to understand and implement.☆53Updated 3 years ago
- code for "Feature Importance-aware Transferable Adversarial Attacks"☆80Updated 2 years ago
- Code for "Adversarial Camouflage: Hiding Physical World Attacks with Natural Styles" (CVPR 2020)☆89Updated last year
- Enhancing the Transferability of Adversarial Attacks through Variance Tuning☆85Updated last year
- Codes for ICLR 2020 paper "Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets"☆71Updated 4 years ago
- Our Team (green hand) 6th Solution for CVPR-2021 AIC-VI: Unrestricted Adversarial Attacks on ImageNet☆26Updated 3 years ago
- ☆70Updated 3 years ago
- Official repository for "A Self-supervised Approach for Adversarial Robustness" (CVPR 2020--Oral)☆98Updated 3 years ago
- ☆37Updated 4 years ago
- ☆26Updated 2 years ago
- Implementation of ECCV 2020 "Sparse Adversarial Attack via Perturbation Factorization"☆28Updated 4 years ago
- ☆39Updated 4 years ago
- Official repository for CVPR 2022 paper 'Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution'☆26Updated 2 years ago
- The translation-invariant adversarial attack method to improve the transferability of adversarial examples.☆140Updated last year
- The official implementation of CVPR 2021 paper "Simulating Unknown Target Models for Query-Efficient Black-box Attacks"☆57Updated 3 years ago
- Code for "Adversarial attack by dropping information." (ICCV 2021)☆75Updated 3 years ago
- Simple yet effective targeted transferable attack (NeurIPS 2021)☆48Updated 2 years ago
- Official repository for "Cross-Domain Transferability of Adversarial Perturbations" (NeurIPS 2019)☆59Updated 3 years ago
- ☆34Updated last year
- Codes for CVPR2020 paper "Towards Transferable Targeted Attack".☆15Updated 2 years ago
- ☆25Updated 3 years ago
- Beyond imagenet attack (accepted by ICLR 2022) towards crafting adversarial examples for black-box domains.☆60Updated 2 years ago
- Code for "Diversity can be Transferred: Output Diversification for White- and Black-box Attacks"☆53Updated 4 years ago
- Boosting Transferability through Enhanced Momentum☆14Updated last year
- Pytorch implementation of Adversarial Patch on ImageNet (arXiv: https://arxiv.org/abs/1712.09665)☆59Updated 4 years ago
- [CVPR 2022] Official implementation of the Object-based Diverse Input (ODI) method☆22Updated 2 years ago
- ☆40Updated last year
- The code of our AAAI 2021 paper "Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-transform Domain"☆14Updated 3 years ago
- A PyTorch Implementation of the UAP attack☆19Updated 6 years ago