controllability / jailbreak-evaluation
The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation.
☆22Updated 4 months ago
Alternatives and similar repositories for jailbreak-evaluation:
Users that are interested in jailbreak-evaluation are comparing it to the libraries listed below
- ☆31Updated 4 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆148Updated 3 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆143Updated this week
- LLM security and privacy☆48Updated 5 months ago
- A collection of prompt injection mitigation techniques.☆20Updated last year
- ☆51Updated 2 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆63Updated 11 months ago
- ☆41Updated 4 months ago
- Official repository for the paper "ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming"☆41Updated 6 months ago
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆182Updated 2 months ago
- ☆57Updated 9 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆43Updated 5 months ago
- ☆49Updated 3 weeks ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆81Updated 10 months ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆49Updated 7 months ago
- Papers about red teaming LLMs and Multimodal models.☆105Updated 4 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆51Updated 7 months ago
- ☆19Updated last year
- A prompt injection game to collect data for robust ML research☆55Updated 2 months ago
- Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique☆14Updated 7 months ago
- ☆43Updated 10 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆50Updated 3 weeks ago
- Advancing LLM with Diverse Coding Capabilities☆69Updated 8 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆61Updated last year
- Dataset for the Tensor Trust project☆39Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆125Updated 8 months ago
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆68Updated 2 months ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated 10 months ago
- ☆81Updated last year
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆67Updated last year