reds-lab / Meta-Sift
The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on poisoned dataset.
☆18Updated last year
Related projects ⓘ
Alternatives and complementary repositories for Meta-Sift
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆24Updated this week
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆14Updated last year
- Camouflage poisoning via machine unlearning☆15Updated last year
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆28Updated 10 months ago
- ☆19Updated 2 months ago
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆41Updated 2 years ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆17Updated last year
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆55Updated last year
- A minimal PyTorch implementation of Label-Consistent Backdoor Attacks☆27Updated 3 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆50Updated 2 years ago
- The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consist…☆19Updated last year
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- ☆23Updated last year
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆31Updated last month
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆31Updated 2 years ago
- ☆15Updated 5 months ago
- Anti-Backdoor learning (NeurIPS 2021)☆78Updated last year
- ☆26Updated 2 years ago
- [NeurIPS 2023] Differentially Private Image Classification by Learning Priors from Random Processes☆11Updated last year
- APBench: A Unified Availability Poisoning Attack and Defenses Benchmark (TMLR 08/2024)☆27Updated last week
- [ICML 2023] Are Diffusion Models Vulnerable to Membership Inference Attacks?☆31Updated 2 months ago
- ☆17Updated 2 years ago
- Code for identifying natural backdoors in existing image datasets.☆15Updated 2 years ago
- ☆12Updated 3 years ago
- This repo is the official implementation of the ICLR'23 paper "Towards Robustness Certification Against Universal Perturbations." We calc…☆12Updated last year
- Code for Backdoor Attacks Against Dataset Distillation☆30Updated last year
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated last year
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆14Updated last year
- Code for "Label-Consistent Backdoor Attacks"☆49Updated 3 years ago
- ☆28Updated 2 years ago