walledai / walledeval
Test LLMs against jailbreaks and unprecedented harms
☆25Updated 3 months ago
Alternatives and similar repositories for walledeval:
Users that are interested in walledeval are comparing it to the libraries listed below
- ☆16Updated 5 months ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆88Updated 10 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆92Updated 8 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆73Updated 10 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆75Updated 8 months ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆56Updated last month
- Papers about red teaming LLMs and Multimodal models.☆91Updated last month
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆112Updated 6 months ago
- [ACL 2024] LangBridge: Multilingual Reasoning Without Multilingual Supervision☆83Updated 2 months ago
- A collection of automated evaluators for assessing jailbreak attempts.☆92Updated last week
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆51Updated 2 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆66Updated 10 months ago
- Improving Alignment and Robustness with Circuit Breakers☆174Updated 3 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆39Updated 2 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆155Updated 3 months ago
- Dataset for the Tensor Trust project☆35Updated 10 months ago
- This repository contains the official code for the paper: "Prompt Injection: Parameterization of Fixed Inputs"☆32Updated 4 months ago
- Official repository for the paper "ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming"☆36Updated 3 months ago
- ☆15Updated 3 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆85Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆64Updated 7 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆64Updated 10 months ago
- Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique☆11Updated 4 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆88Updated last month
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆77Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆247Updated 3 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆58Updated 11 months ago
- Code for the paper "Fishing for Magikarp"☆139Updated this week
- ☆50Updated 2 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆65Updated 10 months ago