tianyu139 / friendly-noiseLinks
Code for Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks (NeurIPS 2022)
☆9Updated last year
Alternatives and similar repositories for friendly-noise
Users that are interested in friendly-noise are comparing it to the libraries listed below
Sorting:
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆15Updated 2 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆53Updated 2 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Updated 6 months ago
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆20Updated 8 months ago
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆44Updated 3 years ago
- Not All Poisons are Created Equal: Robust Training against Data Poisoning (ICML 2022)☆20Updated 2 years ago
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆35Updated 7 months ago
- Official implementation of "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" (ICLR 2022)☆50Updated 2 years ago
- ☆20Updated last year
- Camouflage poisoning via machine unlearning☆17Updated 2 years ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆32Updated 2 years ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 3 years ago
- ☆25Updated 2 years ago
- Backdoor Cleansing with Unlabeled Data (CVPR 2023)☆13Updated 2 years ago
- ☆65Updated last year
- ☆11Updated 2 years ago
- APBench: A Unified Availability Poisoning Attack and Defenses Benchmark (TMLR 08/2024)☆30Updated last month
- ☆34Updated last year
- Public implementation of the paper "On the Importance of Difficulty Calibration in Membership Inference Attacks".☆15Updated 3 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 …☆18Updated 2 years ago
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated 2 years ago
- ☆44Updated last year
- ☆12Updated last year
- ☆57Updated last year
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆32Updated 2 years ago
- [ICML 2023] Are Diffusion Models Vulnerable to Membership Inference Attacks?☆36Updated 9 months ago
- ☆15Updated 2 years ago
- ☆10Updated 5 months ago
- ☆17Updated 3 years ago
- ☆51Updated 3 years ago