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
Alternatives and similar repositories for MOTH:
Users that are interested in MOTH are comparing it to the libraries listed below
- [NDSS'23] BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense☆17Updated 10 months ago
- ☆15Updated 2 years ago
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models☆16Updated 3 months ago
- [CVPR'24] LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning☆12Updated 2 months ago
- [IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks☆21Updated 3 months ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 2 years ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆14Updated last year
- ☆13Updated 3 years ago
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆28Updated 3 months ago
- ☆11Updated 2 years ago
- Official Implementation of NeurIPS 2024 paper - BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens☆13Updated 2 weeks ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- A toolbox for backdoor attacks.☆21Updated 2 years ago
- Siren: Byzantine-robust Federated Learning via Proactive Alarming (SoCC '21)☆11Updated last year
- ☆17Updated 6 months ago
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆14Updated 2 years ago
- Machine Learning & Security Seminar @Purdue University☆25Updated last year
- ☆23Updated 2 years ago
- 🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access☆19Updated 4 months ago
- ☆11Updated 2 years ago
- [NDSS 2025] CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling☆11Updated 2 months ago
- Code for identifying natural backdoors in existing image datasets.☆15Updated 2 years ago
- Code release for DeepJudge (S&P'22)☆51Updated 2 years ago
- ☆20Updated last year
- Code release for RobOT (ICSE'21)☆15Updated 2 years ago
- AdvDoor: Adversarial Backdoor Attack of Deep Learning System☆31Updated 4 months ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆57Updated last year
- This is the source code for HufuNet. Our paper is accepted by the IEEE TDSC.☆22Updated last year
- ☆13Updated 11 months ago
- ☆19Updated 2 years ago