uw-nsl / SafeDecoding
Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
☆121Updated 8 months ago
Alternatives and similar repositories for SafeDecoding:
Users that are interested in SafeDecoding are comparing it to the libraries listed below
- ☆167Updated last year
- ☆79Updated last month
- 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☆145Updated 10 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆78Updated 10 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆73Updated last year
- Weak-to-Strong Jailbreaking on Large Language Models☆72Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆90Updated 10 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆48Updated 5 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆134Updated 2 weeks ago
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆45Updated 2 years ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆88Updated 6 months ago
- ☆119Updated 6 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆123Updated last month
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆48Updated 6 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆59Updated 2 months ago
- ☆92Updated last year
- ☆43Updated 9 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆58Updated 2 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆93Updated last month
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆91Updated 7 months ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆26Updated 4 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…☆281Updated last year
- Accepted by ECCV 2024☆112Updated 5 months ago
- Papers about red teaming LLMs and Multimodal models.☆105Updated 4 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆97Updated 2 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆79Updated 2 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆127Updated 3 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆102Updated last month
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆63Updated 5 months ago