LLMSecurity / MasterKeyLinks
MASTERKEY is a framework designed to explore and exploit vulnerabilities in large language model chatbots by automating jailbreak attacks and evaluating their defenses.
☆26Updated 10 months ago
Alternatives and similar repositories for MasterKey
Users that are interested in MasterKey are comparing it to the libraries listed below
Sorting:
- [USENIX'24] Prompt Stealing Attacks Against Text-to-Image Generation Models☆41Updated 6 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆15Updated 3 months ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆39Updated last year
- ☆32Updated 9 months ago
- A toolbox for backdoor attacks.☆22Updated 2 years ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆25Updated last year
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆50Updated 9 months ago
- ☆49Updated last year
- ☆25Updated 11 months ago
- ☆18Updated 2 years ago
- This is an official repository for Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study (ICCV2023…☆23Updated last year
- ☆22Updated last year
- [NDSS'25] The official implementation of safety misalignment.☆16Updated 7 months ago
- ☆20Updated last year
- 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
- ☆17Updated 4 months ago
- ☆12Updated last week
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆58Updated 2 years ago
- Repository for Towards Codable Watermarking for Large Language Models☆38Updated last year
- This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.☆58Updated 7 months ago
- ☆31Updated 3 years ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated last year
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆16Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆85Updated 10 months ago
- ☆58Updated 2 months ago
- ☆35Updated 10 months ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆36Updated last year
- ☆31Updated 2 months ago
- ☆30Updated last year
- ☆20Updated last year