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.
☆17Updated 2 years ago
Alternatives and similar repositories for ASSET
Users that are interested in ASSET are comparing it to the libraries listed below
Sorting:
- 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
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆38Updated last year
- A toolbox for backdoor attacks.☆22Updated 2 years ago
- ☆16Updated 2 years ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 3 years ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆58Updated 2 years ago
- ☆31Updated 3 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆53Updated 2 years ago
- ☆11Updated 2 years ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆16Updated last year
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Updated 7 months ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated 10 months ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- ☆23Updated 2 years ago
- ☆21Updated last year
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆14Updated 2 years ago
- [NDSS'23] BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense☆17Updated last year
- ☆19Updated 2 years ago
- ☆19Updated 9 months ago
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models☆17Updated 5 months ago
- Anti-Backdoor learning (NeurIPS 2021)☆81Updated last year
- This is the source code for MEA-Defender. Our paper is accepted by the IEEE Symposium on Security and Privacy (S&P) 2024.☆23Updated last year
- ☆66Updated 4 years ago
- A minimal PyTorch implementation of Label-Consistent Backdoor Attacks