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:
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆61Updated 4 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆97Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆105Updated 8 months ago
- ☆121Updated last year
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆83Updated last year
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆39Updated last year
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆110Updated last year
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆60Updated last year
- Fingerprint large language models☆49Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆107Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆74Updated 11 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆66Updated last year
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆58Updated 4 months ago
- ☆23Updated 7 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆29Updated last year
- Red Queen Dataset and data generation template☆25Updated last month
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆109Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆153Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆174Updated last year
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆85Updated 8 months ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆33Updated last year
- ☆71Updated 10 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆23Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆98Updated last year
- ☆173Updated 3 months ago
- ☆63Updated 8 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆108Updated last year
- S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models☆108Updated 3 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆34Updated last year