RobustNLP / DeRTaLinks
A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.
☆73Updated 7 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☆152Updated last year
- ☆191Updated 2 years ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆91Updated 8 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆33Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆98Updated last year
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆117Updated last year
- ☆85Updated 4 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆95Updated 7 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆169Updated 9 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆150Updated 4 months ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆102Updated last year
- 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…☆337Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆122Updated 10 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆173Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 11 months ago
- ☆117Updated 11 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆32Updated last year
- ☆158Updated last year
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆66Updated last year
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆157Updated last year
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆97Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆78Updated 5 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆120Updated 10 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆60Updated 3 months ago
- ☆114Updated 2 years ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆182Updated 8 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆91Updated last year
- The official repository for guided jailbreak benchmark☆27Updated 5 months ago
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆55Updated 2 years ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆73Updated 10 months ago