reds-lab / ASSETLinks
This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms." ASSET achieves state-of-the-art reliability in detecting poisoned samples in end-to-end supervised learning/ self-supervised learning/ transfer learning.
☆19Updated 2 years ago
Alternatives and similar repositories for ASSET
Users that are interested in ASSET are comparing it to the libraries listed below
Sorting:
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆39Updated last year
- 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
- ☆31Updated 3 years ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆58Updated 2 years ago
- ☆27Updated 2 years ago
- ☆25Updated 2 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Updated 9 months ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 3 years ago
- ☆11Updated 2 years ago
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆14Updated 2 years ago
- ☆13Updated 3 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆53Updated 2 years ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated last year
- ☆66Updated 4 years ago
- Anti-Backdoor learning (NeurIPS 2021)☆82Updated 2 years ago
- ☆20Updated last year
- Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples☆27Updated 2 years ago
- ☆83Updated 4 years ago
- ☆19Updated 11 months ago
- Code Repository for the Paper ---Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023)☆44Updated 2 years ago
- Camouflage poisoning via machine unlearning☆17Updated 2 months ago
- Code for identifying natural backdoors in existing image datasets.☆15Updated 3 years ago
- ☆18Updated 3 years ago
- ☆18Updated 4 years ago
- This is the source code for MEA-Defender. Our paper is accepted by the IEEE Symposium on Security and Privacy (S&P) 2024.☆26Updated last year
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆17Updated last year
- Code for Backdoor Attacks Against Dataset Distillation☆35Updated 2 years ago
- ☆25Updated 2 years ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆39Updated last year