Gwinhen / MOTH
This is the implementation for IEEE S&P 2022 paper "Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Security."
☆11Updated 2 years ago
Related projects: ⓘ
- ☆13Updated 2 years ago
- [NDSS'23] BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense☆14Updated 4 months ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆23Updated 2 years ago
- Exploring the Orthogonality and Linearity of Backdoor Attacks [IEEE S&P 2024]☆16Updated last month
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated 11 months ago
- ☆12Updated 2 years ago
- ☆16Updated 3 years ago
- Code release for DeepJudge (S&P'22)☆50Updated last year
- ☆60Updated 3 years ago
- AdvDoor: Adversarial Backdoor Attack of Deep Learning System☆30Updated last year
- ☆23Updated last year
- ☆20Updated last year
- ☆14Updated 2 years ago
- Machine Learning & Security Seminar @Purdue University☆25Updated last year
- [S&P'24] Test-Time Poisoning Attacks Against Test-Time Adaptation Models☆14Updated 7 months ago
- ☆23Updated last year
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆28Updated 3 months ago
- ☆11Updated 2 years ago
- ☆27Updated 2 years ago
- ☆73Updated 3 years ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆16Updated last year
- ☆18Updated 3 years ago
- Code for identifying natural backdoors in existing image datasets.☆14Updated 2 years ago
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆13Updated last year
- Code release for RobOT (ICSE'21)☆14Updated last year
- Code for NDSS 2022 paper "MIRROR: Model Inversion for Deep Learning Network with High Fidelity"☆20Updated last year
- ☆10Updated 3 years ago
- A minimal PyTorch implementation of Label-Consistent Backdoor Attacks☆25Updated 3 years ago
- ☆14Updated 5 years ago
- ☆19Updated 4 years ago