reds-lab / ASSET
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 last year
Alternatives and similar repositories for ASSET:
Users that are interested in ASSET are comparing it to the libraries listed below
- 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 last year
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆34Updated last year
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 2 years ago
- ☆26Updated 2 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆54Updated 2 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆25Updated 2 months ago
- A toolbox for backdoor attacks.☆20Updated 2 years ago
- ☆31Updated 2 years ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆14Updated last year
- ☆24Updated last year
- ☆13Updated 3 years ago
- ☆11Updated 2 years ago
- ☆21Updated 3 months ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆57Updated last year
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆14Updated 2 years ago
- ☆14Updated 2 years ago
- ☆18Updated 2 years ago
- This repo is the official implementation of the ICLR'23 paper "Towards Robustness Certification Against Universal Perturbations." We calc…☆12Updated last year
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples☆23Updated last year
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆14Updated 5 months ago
- Anti-Backdoor learning (NeurIPS 2021)☆81Updated last year
- ☆18Updated 7 months ago
- [IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks☆19Updated last month
- This is the source code for MEA-Defender. Our paper is accepted by the IEEE Symposium on Security and Privacy (S&P) 2024.☆18Updated last year
- This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.☆53Updated last month
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆14Updated 2 years ago
- ☆19Updated 2 years ago
- AdvDoor: Adversarial Backdoor Attack of Deep Learning System☆32Updated 2 months ago
- Camouflage poisoning via machine unlearning☆16Updated 2 years ago