RobustNLP / DeRTaLinks
A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.
☆71Updated 8 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☆151Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆92Updated 9 months ago
- ☆193Updated 2 years ago
- ☆121Updated last year
- 【ACL 2024】 SALAD benchmark & MD-Judge☆171Updated 10 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆98Updated last year
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆99Updated 3 weeks ago
- ☆94Updated 5 months ago
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆118Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆83Updated 6 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated last year
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆32Updated last year
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆34Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆123Updated 11 months ago
- ☆174Updated 3 months ago
- ☆162Updated last year
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆160Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆126Updated 11 months ago
- The repository of the paper "REEF: Representation Encoding Fingerprints for Large Language Models," aims to protect the IP of open-source…☆74Updated last year
- The official repository for guided jailbreak benchmark☆28Updated 6 months ago
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆70Updated 2 years ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆97Updated last year
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆152Updated 5 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆174Updated last year
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆66Updated last year
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆33Updated last year
- ☆120Updated 2 years ago
- ☆47Updated 2 weeks 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…☆338Updated last year
- Panda Guard is designed for researching jailbreak attacks, defenses, and evaluation algorithms for large language models (LLMs).☆61Updated 2 weeks ago