RobustNLP / DeRTaLinks
A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.
☆65Updated 3 months ago
Alternatives and similar repositories for DeRTa
Users that are interested in DeRTa are comparing it to the libraries listed below
Sorting:
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆143Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆85Updated 4 months ago
- ☆183Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆97Updated last year
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆30Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆64Updated 8 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆88Updated 4 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆161Updated 6 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆70Updated last month
- ☆110Updated 4 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆31Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆96Updated 4 months ago
- ☆102Updated 7 months ago
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆114Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆102Updated 7 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆86Updated last year
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆82Updated last year
- ☆56Updated last month
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆57Updated last week
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆55Updated 2 years ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆164Updated last year
- ☆148Updated last year
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆148Updated 9 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆111Updated 6 months ago
- SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types☆21Updated 9 months ago
- [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"☆19Updated 11 months ago
- LLM Unlearning☆174Updated last year
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆151Updated 5 months ago
- Multilingual safety benchmark for Large Language Models☆52Updated last year
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆91Updated 9 months ago