LLMSecurity / MasterKey
MASTERKEY is a framework designed to explore and exploit vulnerabilities in large language model chatbots by automating jailbreak attacks and evaluating their defenses.
☆20Updated 6 months ago
Alternatives and similar repositories for MasterKey:
Users that are interested in MasterKey are comparing it to the libraries listed below
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated 7 months ago
- ☆24Updated 5 months ago
- ☆28Updated 6 months ago
- Composite Backdoor Attacks Against Large Language Models☆13Updated 11 months ago
- ☆19Updated 9 months ago
- ☆46Updated 3 months ago
- ☆20Updated last year
- A toolbox for backdoor attacks.☆21Updated 2 years ago
- [NDSS 2025] Official code for our paper "Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Wate…☆32Updated 4 months ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆24Updated last year
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆14Updated last year
- Official Implementation of NeurIPS 2024 paper - BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens☆13Updated 2 weeks ago
- Repository for Towards Codable Watermarking for Large Language Models☆36Updated last year
- ☆15Updated 2 years ago
- ☆19Updated 2 years ago
- Code for paper: "PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", IEEE S&P 2024.☆30Updated 7 months ago
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆29Updated 2 months ago
- ☆14Updated last year
- This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.☆55Updated 3 months ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆35Updated last year
- BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models☆127Updated last month
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆57Updated last year
- ☆43Updated 7 months ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆25Updated 4 months ago
- ☆21Updated 7 months ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆20Updated 4 months ago
- Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models☆16Updated 2 weeks ago
- ☆79Updated 11 months ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆31Updated 8 months ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆17Updated last year