VITA-Group / Random-Shuffling-BackdoorDetectLinks
[NeurIPS 2022] "Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets" by Ruisi Cai*, Zhenyu Zhang*, Tianlong Chen, Xiaohan Chen, Zhangyang Wang
☆20Updated 2 years ago
Alternatives and similar repositories for Random-Shuffling-BackdoorDetect
Users that are interested in Random-Shuffling-BackdoorDetect are comparing it to the libraries listed below
Sorting:
- [NeurIPS'22] Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. Haotao Wang, Junyuan Hong,…☆15Updated last year
- [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
- ☆19Updated 4 years ago
- ☆11Updated 3 years ago
- Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at IC…☆27Updated 5 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Updated 9 months ago
- [ICLR 2023, Spotlight] Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning☆31Updated last year
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆15Updated 2 years ago
- Not All Poisons are Created Equal: Robust Training against Data Poisoning (ICML 2022)☆20Updated 3 years ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆32Updated 2 years ago
- Robustify Black-Box Models (ICLR'22 - Spotlight)☆24Updated 2 years ago
- ☆11Updated 2 years ago
- ☆24Updated 2 years ago
- kyleliang919 / Uncovering-the-Connections-BetweenAdversarial-Transferability-and-Knowledge-Transferabilitycode for ICML 2021 paper in which we explore the relationship between adversarial transferability and knowledge transferability.☆17Updated 2 years ago
- [NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training☆31Updated 3 years ago
- ☆32Updated 3 years ago
- Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"☆26Updated 3 years ago
- Official implementation of the CVPR 2022 paper "Backdoor Attacks on Self-Supervised Learning".☆74Updated last year
- [ICLR 2021] "Robust Overfitting may be mitigated by properly learned smoothening" by Tianlong Chen*, Zhenyu Zhang*, Sijia Liu, Shiyu Chan…☆47Updated 3 years ago
- ☆13Updated 3 years ago
- On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]☆36Updated 4 years ago
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆19Updated 2 years ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- Implementation for <Robust Weight Perturbation for Adversarial Training> in IJCAI'22.☆15Updated 3 years ago
- ☆53Updated 2 years ago
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated 2 years ago
- Code for identifying natural backdoors in existing image datasets.☆15Updated 3 years ago
- Camouflage poisoning via machine unlearning☆17Updated last month
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆33Updated 2 years ago
- Data-Efficient Backdoor Attacks☆18Updated 3 years ago