declare-lab / red-instruct
Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
☆90Updated 11 months ago
Alternatives and similar repositories for red-instruct:
Users that are interested in red-instruct are comparing it to the libraries listed below
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆117Updated 7 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆77Updated 9 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆84Updated last week
- Weak-to-Strong Jailbreaking on Large Language Models☆72Updated 11 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆84Updated 5 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆66Updated 11 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆124Updated 2 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆70Updated 11 months ago
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆42Updated 2 years ago
- ☆25Updated 4 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆140Updated 9 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
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆46Updated 5 months ago
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆87Updated 6 months ago
- ☆163Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆89Updated 8 months ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆122Updated last year
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆55Updated 3 months ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆24Updated 3 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆69Updated 4 months ago
- ☆74Updated 2 weeks ago
- [ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models☆79Updated 5 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆75Updated last month
- SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors☆43Updated 7 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆88Updated last year
- [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"☆19Updated 4 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆56Updated last month
- ☆44Updated 9 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆84Updated 9 months ago