guanjiyang / SAC
☆16Updated last year
Related projects: ⓘ
- The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consist…☆19Updated last year
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆14Updated last year
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆38Updated 2 years ago
- Removing Adversarial Noise in Class Activation Feature Space☆12Updated 11 months ago
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆18Updated last week
- [CCS'22] SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders☆14Updated 2 years ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆14Updated 5 months ago
- CVPR2023: Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples☆20Updated last year
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated last year
- ☆42Updated 11 months ago
- Code for Prior-Guided Adversarial Initialization for Fast Adversarial Training (ECCV2022)☆23Updated last year
- ☆17Updated 2 years ago
- Official implementation of the ICCV2023 paper: Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregatio…☆21Updated last year
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆30Updated 2 months ago
- The official implementation of the paper "Free Fine-tuning: A Plug-and-Play Watermarking Scheme for Deep Neural Networks".☆14Updated 5 months ago
- ☆27Updated 2 years ago
- Implementation of the paper "MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation".☆28Updated 2 years ago
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆28Updated last year
- ☆14Updated 3 months ago
- ☆20Updated last year
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆49Updated last year
- code for "Feature Importance-aware Transferable Adversarial Attacks"☆73Updated 2 years ago
- [NeurIPS 2023] Boosting Adversarial Transferability by Achieving Flat Local Maxima☆26Updated 6 months ago
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆40Updated 5 months ago
- ☆18Updated this week
- Code for Transferable Unlearnable Examples☆17Updated last year
- Simple yet effective targeted transferable attack (NeurIPS 2021)☆47Updated last year
- A curated list of papers for the transferability of adversarial examples☆47Updated 2 months ago
- Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks(CVPR2023)☆17Updated last year
- PyTorch implementation of our ICLR 2023 paper titled "Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?".☆12Updated last year