uw-nsl / SafeDecoding
Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
☆120Updated 7 months ago
Alternatives and similar repositories for SafeDecoding:
Users that are interested in SafeDecoding are comparing it to the libraries listed below
- ☆77Updated last month
- ☆165Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆89Updated 9 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆72Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆77Updated 10 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆86Updated 6 months ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆95Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆144Updated 10 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆85Updated 2 weeks ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆94Updated last month
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆72Updated 11 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆27Updated 6 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆47Updated 4 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆57Updated 2 months ago
- ☆41Updated 9 months ago
- Python package for measuring memorization in LLMs.☆144Updated 3 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆71Updated 2 weeks ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆47Updated 6 months ago
- ☆91Updated last year
- [NDSS'25 Poster] A collection of automated evaluators for assessing jailbreak attempts.☆120Updated this week
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆117Updated 2 weeks ago
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆89Updated 7 months ago
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆280Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆61Updated 5 months ago
- ☆117Updated 6 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆132Updated this week
- A survey on harmful fine-tuning attack for large language model☆147Updated this week
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆67Updated last year
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆42Updated 2 years ago
- Accepted by ECCV 2024☆109Updated 4 months ago