xirui-li / DrAttack
Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
☆30Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for DrAttack
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆46Updated 3 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆38Updated 3 weeks ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆41Updated last month
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆60Updated 7 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆83Updated 5 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆120Updated 6 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆64Updated 8 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆96Updated 3 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆23Updated last year
- 【ACL 2024】 SALAD benchmark & MD-Judge☆103Updated 3 weeks ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆44Updated last week
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆69Updated 2 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆55Updated 3 months ago
- ☆153Updated 11 months ago
- A collection of automated evaluators for assessing jailbreak attempts.☆71Updated 4 months ago
- LLM Unlearning☆123Updated last year
- Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆58Updated last month
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆61Updated 8 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆50Updated 3 months ago
- ☆38Updated last week
- ☆39Updated 6 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆60Updated last month
- ☆31Updated 4 months ago
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆76Updated 3 months ago
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆16Updated 2 weeks ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆70Updated 6 months ago
- ☆66Updated 11 months ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆111Updated last year
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆24Updated 2 months ago
- ☆38Updated last year