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☆38Updated 9 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]☆98Updated last year
- ☆110Updated 9 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆29Updated last year
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆93Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆99Updated 5 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆32Updated last year
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆105Updated 9 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆58Updated 2 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆75Updated last year
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆64Updated last year
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆59Updated last year
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆54Updated last month
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆22Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆65Updated 8 months ago
- ☆127Updated 2 weeks ago
- Official Code for ACL 2024 paper "GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis"☆60Updated last year
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆107Updated last year
- ☆63Updated 7 months ago
- Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting☆18Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆107Updated last year
- ☆37Updated 5 months ago
- ☆188Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆146Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 10 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆153Updated 11 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆88Updated last year
- S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models☆102Updated last month
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆169Updated last year