ThuCCSLab / MergeGuardLinks
[CCS-LAMPS'24] LLM IP Protection Against Model Merging
☆15Updated 8 months ago
Alternatives and similar repositories for MergeGuard
Users that are interested in MergeGuard are comparing it to the libraries listed below
Sorting:
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Updated 7 months ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 11 months ago
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆19Updated 2 years ago
- ☆20Updated 6 months ago
- [S&P'24] Test-Time Poisoning Attacks Against Test-Time Adaptation Models☆18Updated 4 months ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated 10 months ago
- ☆12Updated last year
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆10Updated 7 months ago
- This is the repository that introduces research topics related to protecting intellectual property (IP) of AI from a data-centric perspec…☆22Updated last year
- ☆16Updated 3 months ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆38Updated last year
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆55Updated last year
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆32Updated 6 months ago
- [NeurIPS 2023] Differentially Private Image Classification by Learning Priors from Random Processes☆12Updated 2 years ago
- ☆34Updated 2 months ago
- Unofficial implementation of "Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection"☆19Updated 11 months ago
- ☆1Updated last year
- ☆19Updated last year
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆24Updated 11 months ago
- Code for paper: "PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", IEEE S&P 2024.☆32Updated 10 months ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆37Updated 11 months ago
- Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.☆32Updated 7 months ago
- ☆13Updated 3 years ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆14Updated last month
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆29Updated 3 weeks ago
- Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Models☆17Updated 8 months ago
- ☆23Updated 2 years ago
- ICL backdoor attack☆13Updated 7 months ago
- ☆21Updated 3 months ago
- ☆31Updated 3 years ago