SolidShen / BAITLinks
π₯π₯π₯ Detecting hidden backdoors in Large Language Models with only black-box access
β30Updated 3 weeks ago
Alternatives and similar repositories for BAIT
Users that are interested in BAIT are comparing it to the libraries listed below
Sorting:
- β16Updated 9 months ago
- β28Updated 8 months ago
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Modelsβ17Updated 5 months ago
- β24Updated 10 months ago
- Siren: Byzantine-robust Federated Learning via Proactive Alarming (SoCC '21)β11Updated last year
- β16Updated 2 years ago
- Machine Learning & Security Seminar @Purdue Universityβ25Updated 2 years ago
- A toolbox for backdoor attacks.β22Updated 2 years ago
- [CVPR'24] LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioningβ15Updated 5 months ago
- [NDSS'23] BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defenseβ17Updated last year
- Official Implementation of NeurIPS 2024 paper - BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokensβ18Updated 3 months ago
- Distribution Preserving Backdoor Attack in Self-supervised Learningβ16Updated last year
- β34Updated 8 months ago
- [NDSS 2025] "CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models"β15Updated 6 months ago
- Code for paper "The Philosopherβs Stone: Trojaning Plugins of Large Language Models"β18Updated 9 months ago
- β82Updated last year
- β20Updated last year
- The code will be released soon!β6Updated 3 years ago
- β19Updated last year
- β58Updated 6 months ago
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)β34Updated 2 months ago
- [Oakland 2024] Exploring the Orthogonality and Linearity of Backdoor Attacksβ25Updated 2 months ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learningβ¦β17Updated 2 years ago
- The most comprehensive and accurate LLM jailbreak attack benchmark by farβ19Updated 3 months ago
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agaiβ¦β47Updated 3 months ago
- β66Updated 4 years ago
- β24Updated 3 years ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Modelsβ37Updated 11 months ago
- β21Updated last year
- β27Updated 2 years ago