Alternatives and similar repositories for ASTRAL

Users that are interested in ASTRAL are comparing it to the libraries listed below

• AIM-Intelligence / Automated-Multi-Turn-Jailbreaks
  ☆94Updated 11 months ago
• sunblaze-ucb / cybergym
  CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on…
  ☆86Updated last month
• llm-platform-security / SecGPT
  An Execution Isolation Architecture for LLM-Based Agentic Systems
  ☆97Updated 9 months ago
• controllability / jailbreak-evaluation
  The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation.
  ☆27Updated last year
• CryptoAILab / JailbreakEval
  [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.
  ☆172Updated 7 months ago
• andyzorigin / cybench
  ☆165Updated 4 months ago
• briland / LLM-security-and-privacy
  LLM security and privacy
  ☆51Updated last year
• LostOxygen / llm-confidentiality
  Whispers in the Machine: Confidentiality in Agentic Systems
  ☆41Updated this week
• uiuc-kang-lab / InjecAgent
  ☆89Updated last year
• invariantlabs-ai / invariant-gateway
  LLM proxy to observe and debug what your AI agents are doing.
  ☆52Updated 3 months ago
• ZenGuard-AI / fast-llm-security-guardrails
  The fastest Trust Layer for AI Agents
  ☆144Updated 5 months ago
• yuchen814 / CodeHalu
  ☆17Updated last year
• HumanCompatibleAI / tensor-trust
  A prompt injection game to collect data for robust ML research
  ☆65Updated 9 months ago
• Libr-AI / OpenRedTeaming
  Papers about red teaming LLMs and Multimodal models.
  ☆152Updated 5 months ago
• liu00222 / Open-Prompt-Injection
  This repository provides a benchmark for prompt injection attacks and defenses
  ☆330Updated last week
• microsoft / TaskTracker
  TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…
  ☆74Updated 2 months ago
• jpmorganchase / CyberBench
  CyberBench: A Multi-Task Cyber LLM Benchmark
  ☆24Updated 6 months ago
• CS-EVAL / CS-Eval
  CS-Eval is a comprehensive evaluation suite for fundamental cybersecurity models or large language models' cybersecurity ability.
  ☆54Updated 11 months ago
• XHMY / AutoDefense
  AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
  ☆56Updated 5 months ago
• AI-secure / AgentPoison
  [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
  ☆163Updated 6 months ago
• ethz-spylab / agentdojo
  A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
  ☆340Updated last week
• thu-coai / Backdoor-Data-Extraction
  ☆29Updated 5 months ago
• facebookresearch / SecAlign
  Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"
  ☆74Updated 3 months ago
• SproutNan / AI-Safety_Benchmark
  The official repository for guided jailbreak benchmark
  ☆24Updated 3 months ago
• declare-lab / ferret
  Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
  ☆18Updated last year
• PurCL / ASTRA
  🥇 Amazon Nova AI Challenge Winner - ASTRA emerged victorious as the top attacking team in Amazon's global AI safety competition, defeati…
  ☆62Updated 2 months ago
• morpheuslord / CVE-llm_dataset
  This is a dataset intended to train a LLM model for a completely CVE focused input and output.
  ☆63Updated 4 months ago
• agiresearch / ASB
  Agent Security Bench (ASB)
  ☆141Updated last week
• lve-org / lve
  A repository of Language Model Vulnerabilities and Exposures (LVEs).
  ☆112Updated last year
• RobustNLP / DeRTa
  A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.
  ☆70Updated 5 months ago