Gwinhen / DRUPE
Distribution Preserving Backdoor Attack in Self-supervised Learning
☆11Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for DRUPE
- ☆13Updated 2 years ago
- [IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks☆17Updated last month
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models☆11Updated 5 months ago
- [NDSS'23] BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense☆14Updated 6 months ago
- A toolbox for backdoor attacks.☆19Updated last year
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 2 years ago
- ☆20Updated 9 months ago
- ☆17Updated 2 years ago
- ☆16Updated 3 years ago
- ☆12Updated 3 years ago
- ☆15Updated 6 months ago
- Code for identifying natural backdoors in existing image datasets.☆15Updated 2 years ago
- ☆17Updated 3 weeks ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆28Updated 10 months ago
- An Embarrassingly Simple Backdoor Attack on Self-supervised Learning☆17Updated 9 months ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆17Updated last year
- ☆25Updated 2 years ago
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆28Updated 4 months ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆55Updated last year
- 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
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆50Updated last year
- Code for NDSS 2022 paper "MIRROR: Model Inversion for Deep Learning Network with High Fidelity"☆22Updated last year
- Stable Backdoor Purification (NeurIPS 2023 & 2024)☆23Updated this week
- This is the repository for USENIX Security 2023 paper "Hard-label Black-box Universal Adversarial Patch Attack".☆14Updated 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.☆15Updated 11 months ago
- [NeurIPS 2023] Differentially Private Image Classification by Learning Priors from Random Processes☆11Updated 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 …☆18Updated last year
- ☆13Updated 2 months ago
- ☆22Updated last year
- A minimal PyTorch implementation of Label-Consistent Backdoor Attacks☆27Updated 3 years ago