Trust4AI / ASTRALLinks
Automated Safety Testing of Large Language Models
☆16Updated 6 months ago
Alternatives and similar repositories for ASTRAL
Users that are interested in ASTRAL are comparing it to the libraries listed below
Sorting:
- ☆82Updated 8 months ago
- ☆27Updated 2 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆165Updated 4 months ago
- The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation.☆25Updated 9 months ago
- ☆70Updated last year
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆86Updated 6 months ago
- LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models☆21Updated last week
- This repository provides a benchmark for prompt Injection attacks and defenses☆255Updated 3 weeks ago
- ☆46Updated 2 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆90Updated last year
- CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on…☆49Updated last week
- Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique☆18Updated 11 months ago
- LLM security and privacy☆49Updated 9 months ago
- Whispers in the Machine: Confidentiality in Agentic Systems☆39Updated 2 months ago
- Papers about red teaming LLMs and Multimodal models.☆132Updated 2 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆144Updated 8 months ago
- 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
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆62Updated 5 months ago
- CS-Eval is a comprehensive evaluation suite for fundamental cybersecurity models or large language models' cybersecurity ability.☆43Updated 8 months ago
- ☆97Updated 3 months ago
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆51Updated 2 months ago
- The fastest Trust Layer for AI Agents☆141Updated 2 months ago
- ☆130Updated 2 months ago
- ☆144Updated 11 months ago
- CyberBench: A Multi-Task Cyber LLM Benchmark☆17Updated 3 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆162Updated 7 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆76Updated last year
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆137Updated 4 months ago
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts☆513Updated 10 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆56Updated 11 months ago