RobustNLP / DeRTaLinks
A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.
☆63Updated 2 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☆141Updated last year
- ☆179Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆84Updated 3 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆96Updated last year
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆84Updated 2 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 6 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆156Updated 5 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆30Updated 11 months ago
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆111Updated last year
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆137Updated 3 months ago
- ☆97Updated 6 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆29Updated last year
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆144Updated 8 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆159Updated last year
- ☆99Updated 3 months ago
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆53Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆98Updated 5 months ago
- ☆144Updated 11 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…☆317Updated last year
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆56Updated 11 months ago
- ☆31Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆165Updated 4 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆79Updated last year
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆54Updated 2 years ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆106Updated 5 months ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆87Updated 8 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆85Updated last year
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆123Updated 6 months ago
- Official Implementation of RISE (Reinforcing Reasoning with Self-Verification)☆28Updated last month
- Official implementation repository for the paper Towards General Conceptual Model Editing via Adversarial Representation Engineering.☆18Updated 8 months ago