Raytsang123 / CLIBELinks
[NDSS 2025] "CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models"
☆16Updated 7 months ago
Alternatives and similar repositories for CLIBE
Users that are interested in CLIBE are comparing it to the libraries listed below
Sorting:
- ☆25Updated 11 months ago
- Repository for Towards Codable Watermarking for Large Language Models☆38Updated last year
- ☆82Updated last year
- ☆18Updated 2 years ago
- 🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access☆35Updated 2 months ago
- ☆22Updated last year
- ☆35Updated 10 months ago
- ☆19Updated last year
- ☆14Updated last year
- [NDSS 2025] Official code for our paper "Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Wate…☆39Updated 9 months ago
- ☆32Updated 9 months ago
- ☆31Updated 4 months ago
- [EMNLP 24] Official Implementation of CLEANGEN: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models☆16Updated 4 months ago
- Official Implementation of NeurIPS 2024 paper - BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens☆23Updated 4 months ago
- ☆223Updated last year
- [USENIX'24] Prompt Stealing Attacks Against Text-to-Image Generation Models☆41Updated 6 months ago
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)☆34Updated last month
- ☆18Updated 3 years ago
- This is the source code for MEA-Defender. Our paper is accepted by the IEEE Symposium on Security and Privacy (S&P) 2024.☆25Updated last year
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆16Updated last year
- ☆15Updated last year
- An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)☆185Updated 2 years ago
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models☆17Updated 7 months ago
- ☆66Updated 4 years ago
- ☆24Updated 2 years ago
- Robust natural language watermarking using invariant features☆26Updated last year
- ☆22Updated last year
- TextGuard: Provable Defense against Backdoor Attacks on Text Classification☆12Updated last year
- ☆20Updated last year
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agai…☆48Updated 4 months ago