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 last year
Alternatives and similar repositories for Trap-and-Replace-Backdoor-Defense:
Users that are interested in Trap-and-Replace-Backdoor-Defense are comparing it to the libraries listed below
- [NeurIPS 2022] "Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets" by Ruisi Cai*, Zhenyu Zh…☆20Updated 2 years ago
- Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at IC…☆27Updated 4 years ago
- ☆11Updated 2 years ago
- ☆19Updated 3 years ago
- [CVPR 2022] "Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free" by Tianlong Chen*, Zhenyu Zhang*, Yihua Zhang*, Shiyu C…☆26Updated 2 years ago
- Not All Poisons are Created Equal: Robust Training against Data Poisoning (ICML 2022)☆19Updated 2 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆25Updated 4 months ago
- Pytorch implementation of NPAttack☆12Updated 4 years ago
- Implementation for <Robust Weight Perturbation for Adversarial Training> in IJCAI'22.☆14Updated 2 years ago
- Pytorch implementation of Adversarially Robust Distillation (ARD)☆59Updated 5 years ago
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆15Updated 2 years ago
- This is the repository that introduces research topics related to protecting intellectual property (IP) of AI from a data-centric perspec…☆22Updated last year
- ☆11Updated 2 years ago
- Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off☆29Updated 2 years ago
- One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks (ICLR 2023 Spotlight)☆13Updated 2 years ago
- [NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training☆31Updated 3 years ago
- SEAT☆20Updated last year
- ☆29Updated 2 years ago
- ☆15Updated last year
- Robustify Black-Box Models (ICLR'22 - Spotlight)☆24Updated 2 years ago
- [NeurIPS 2021] “When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?”☆48Updated 3 years ago
- Code relative to "Adversarial robustness against multiple and single $l_p$-threat models via quick fine-tuning of robust classifiers"☆18Updated 2 years ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆34Updated 5 months ago
- [ICLR 2023, Spotlight] Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning☆30Updated last year
- ☆35Updated 4 years ago
- Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning. (Neurips 2021)☆8Updated 3 years ago
- Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses, NeurIPS Spotlight 2020☆27Updated 4 years ago
- official implementation of Towards Robust Model Watermark via Reducing Parametric Vulnerability☆13Updated 9 months ago
- Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks☆38Updated 3 years ago