SolidShen / BAITLinks
π₯π₯π₯ Detecting hidden backdoors in Large Language Models with only black-box access
β29Updated this week
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
- Machine Learning & Security Seminar @Purdue Universityβ25Updated 2 years ago
- β15Updated 2 years ago
- [CVPR'24] LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioningβ15Updated 4 months ago
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Modelsβ17Updated 5 months ago
- [NDSS'23] BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defenseβ17Updated last year
- A toolbox for backdoor attacks.β22Updated 2 years ago
- β28Updated 7 months ago
- Distribution Preserving Backdoor Attack in Self-supervised Learningβ16Updated last year
- Official Implementation of NeurIPS 2024 paper - BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokensβ18Updated 2 months ago
- Code for paper "The Philosopherβs Stone: Trojaning Plugins of Large Language Models"β17Updated 8 months ago
- β33Updated 8 months ago
- Siren: Byzantine-robust Federated Learning via Proactive Alarming (SoCC '21)β11Updated last year
- [NDSS 2025] "CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models"β15Updated 5 months ago
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)β34Updated last month
- Seminar 2022β21Updated 2 months ago
- β14Updated last year
- β23Updated 9 months ago
- Code release for DeepJudge (S&P'22)β51Updated 2 years ago
- β20Updated last year
- [IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacksβ25Updated last month
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."β24Updated 3 years ago
- β80Updated last year
- [ECCV'24] UNIT: Backdoor Mitigation via Automated Neural Distribution Tighteningβ10Updated 2 months ago
- β57Updated 5 months ago
- β27Updated 2 years ago
- β19Updated last year
- β24Updated 3 years ago
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agaiβ¦β45Updated 2 months ago
- Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samplesβ25Updated last year