HKUST-KnowComp / LLM-Multistep-JailbreakLinks
Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT
☆35Updated 2 years ago
Alternatives and similar repositories for LLM-Multistep-Jailbreak
Users that are interested in LLM-Multistep-Jailbreak are comparing it to the libraries listed below
Sorting:
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆37Updated 9 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆57Updated last month
- ☆106Updated 8 months ago
- Fingerprint large language models☆44Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆93Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆97Updated 5 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆30Updated last year
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆29Updated last year
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆74Updated 11 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆62Updated 7 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆64Updated last year
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆106Updated last year
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆58Updated last year
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆102Updated 9 months ago
- Official Code for ACL 2024 paper "GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis"☆60Updated 11 months ago
- ☆63Updated 6 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆22Updated last year
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆48Updated 3 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆89Updated last year
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆53Updated 3 weeks ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆40Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆146Updated last year
- Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting☆18Updated last year
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆30Updated 11 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆99Updated last year
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆61Updated last year
- ☆41Updated 6 months ago
- Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.☆34Updated 11 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆168Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 9 months ago