SolidShen / BAIT
π₯π₯π₯ Detecting hidden backdoors in Large Language Models with only black-box access
β22Updated 5 months ago
Alternatives and similar repositories for BAIT:
Users that are interested in BAIT are comparing it to the libraries listed below
- β16Updated 8 months ago
- Machine Learning & Security Seminar @Purdue Universityβ25Updated last year
- [NDSS'23] BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defenseβ17Updated 11 months ago
- β15Updated 2 years ago
- [CVPR'24] LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioningβ13Updated 3 months ago
- β26Updated 6 months ago
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Modelsβ17Updated 4 months ago
- Distribution Preserving Backdoor Attack in Self-supervised Learningβ15Updated last year
- This is the implementation for IEEE S&P 2022 paper "Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Securβ¦β12Updated 2 years ago
- Seminar 2022β21Updated last month
- Official repo for FSE'24 paper "CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking"β16Updated last month
- β31Updated 7 months ago
- β18Updated last year
- [NDSS 2025] "CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models"β12Updated 4 months ago
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agaiβ¦β44Updated last month
- β20Updated last year
- Siren: Byzantine-robust Federated Learning via Proactive Alarming (SoCC '21)β11Updated last year
- Code release for DeepJudge (S&P'22)β51Updated 2 years ago
- The code will be released soon!β7Updated 3 years ago
- Official Implementation of NeurIPS 2024 paper - BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokensβ16Updated last month
- β18Updated 2 years ago
- β65Updated 4 years ago
- β15Updated last year
- β21Updated 8 months ago
- A toolbox for backdoor attacks.β21Updated 2 years ago
- Code for paper "The Philosopherβs Stone: Trojaning Plugins of Large Language Models"β17Updated 7 months ago
- β24Updated 3 years ago
- β79Updated last year
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)β33Updated 2 weeks ago
- β27Updated 2 years ago