VITA-Group / Trap-and-Replace-Backdoor-Defense
[NeurIPS'22] Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. Haotao Wang, Junyuan Hong, Aston Zhang, Jiayu Zhou, Zhangyang Wang
☆14Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for Trap-and-Replace-Backdoor-Defense
- [NeurIPS 2022] "Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets" by Ruisi Cai*, Zhenyu Zh…☆19Updated 2 years ago
- Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at IC…☆26Updated 4 years ago
- [CVPR 2022] "Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free" by Tianlong Chen*, Zhenyu Zhang*, Yihua Zhang*, Shiyu C…☆25Updated 2 years ago
- ☆11Updated 2 years ago
- ☆19Updated 3 years ago
- Pytorch implementation of NPAttack☆12Updated 4 years ago
- [NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training☆31Updated 2 years ago
- ☆35Updated 3 years ago
- Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off☆29Updated 2 years ago
- [ICLR 2021] "Robust Overfitting may be mitigated by properly learned smoothening" by Tianlong Chen*, Zhenyu Zhang*, Sijia Liu, Shiyu Chan…☆46Updated 2 years ago
- Pytorch implementation of Adversarially Robust Distillation (ARD)☆59Updated 5 years ago
- Robustify Black-Box Models (ICLR'22 - Spotlight)☆24Updated last year
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆14Updated last year
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- SEAT☆20Updated last year
- [ICLR 2022 official code] Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?☆26Updated 2 years ago
- Code relative to "Adversarial robustness against multiple and single $l_p$-threat models via quick fine-tuning of robust classifiers"☆15Updated last year
- Code for the paper "Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks"☆11Updated 2 years ago
- Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses, NeurIPS Spotlight 2020☆24Updated 3 years ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆28Updated 10 months ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆24Updated this week
- ☆19Updated 2 years ago
- ☆14Updated last year
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆31Updated 2 years ago
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆29Updated last year
- Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks☆37Updated 3 years ago
- One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks (ICLR 2023 Spotlight)☆12Updated last year
- Official implementation of "Removing Batch Normalization Boosts Adversarial Training" (ICML'22)☆19Updated 2 years ago
- Not All Poisons are Created Equal: Robust Training against Data Poisoning (ICML 2022)☆17Updated 2 years ago
- Code for Boosting fast adversarial training with learnable adversarial initialization (TIP2022)☆29Updated last year