declare-lab / red-instruct
Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
☆97Updated last year
Alternatives and similar repositories for red-instruct:
Users that are interested in red-instruct are comparing it to the libraries listed below
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆80Updated 11 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆96Updated last month
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆128Updated 8 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆29Updated 8 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆91Updated 10 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆74Updated last year
- 【ACL 2024】 SALAD benchmark & MD-Judge☆142Updated last month
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆92Updated 8 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆70Updated last year
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆49Updated 2 years ago
- Weak-to-Strong Jailbreaking on Large Language Models☆72Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆90Updated 7 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆150Updated 11 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆60Updated 5 months ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆26Updated 5 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆51Updated 5 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆51Updated last month
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆133Updated last year
- ☆25Updated 6 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆74Updated 2 weeks ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆83Updated 2 months ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆72Updated 4 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆50Updated 8 months ago
- The Paper List on Data Contamination for Large Language Models Evaluation.☆91Updated 2 weeks ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆71Updated last month
- ☆54Updated 2 years ago
- ☆62Updated 3 months ago
- Papers about red teaming LLMs and Multimodal models.☆108Updated 4 months ago
- ☆81Updated 2 months ago
- ☆169Updated last year