Alternatives and similar repositories for ASTRAL

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

• controllability / jailbreak-evaluation
  The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation.
  ☆27Updated last year
• AIM-Intelligence / Automated-Multi-Turn-Jailbreaks
  ☆108Updated last week
• LostOxygen / llm-confidentiality
  Whispers in the Machine: Confidentiality in Agentic Systems
  ☆41Updated this week
• CryptoAILab / JailbreakEval
  [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.
  ☆175Updated 8 months ago
• llm-platform-security / SecGPT
  An Execution Isolation Architecture for LLM-Based Agentic Systems
  ☆100Updated 10 months ago
• uiuc-kang-lab / InjecAgent
  ☆97Updated last year
• thu-coai / Backdoor-Data-Extraction
  ☆29Updated 6 months ago
• microsoft / TaskTracker
  TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…
  ☆78Updated 3 months ago
• HumanCompatibleAI / tensor-trust
  A prompt injection game to collect data for robust ML research
  ☆65Updated 10 months ago
• andyzorigin / cybench
  ☆179Updated 6 months ago
• briland / LLM-security-and-privacy
  LLM security and privacy
  ☆52Updated last year
• ZenGuard-AI / fast-llm-security-guardrails
  The fastest Trust Layer for AI Agents
  ☆145Updated 6 months ago
• agiresearch / ASB
  Agent Security Bench (ASB)
  ☆154Updated last month
• XHMY / AutoDefense
  AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
  ☆61Updated 6 months ago
• liu00222 / Open-Prompt-Injection
  This repository provides a benchmark for prompt injection attacks and defenses
  ☆357Updated last month
• Safetorun / PromptDefender
  A prompt defence is a multi-layer defence that can be used to protect your applications against prompt injection attacks.
  ☆20Updated last year
• declare-lab / ferret
  Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
  ☆18Updated last year
• CS-EVAL / CS-Eval
  CS-Eval is a comprehensive evaluation suite for fundamental cybersecurity models or large language models' cybersecurity ability.
  ☆56Updated last year
• xirui-li / DrAttack
  Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
  ☆66Updated last year
• hupe1980 / aisploit
  🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.
  ☆27Updated last year
• Valhall-ai / prompt-injection-mitigations
  A collection of prompt injection mitigation techniques.
  ☆25Updated 2 years ago
• SALT-NLP / PopupAttack
  Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups
  ☆47Updated 11 months ago
• AI-secure / AgentPoison
  [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
  ☆179Updated 8 months ago
• Libr-AI / OpenRedTeaming
  Papers about red teaming LLMs and Multimodal models.
  ☆158Updated 6 months ago
• leondz / lm_risk_cards
  Risks and targets for assessing LLMs & LLM vulnerabilities
  ☆33Updated last year
• usail-hkust / JailTrickBench
  Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)
  ☆155Updated last year
• dukeceicenter / jailbreak-reasoning-openai-o1o3-deepseek-r1
  ☆113Updated 7 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…
  ☆100Updated 2 months ago
• leolee99 / PIGuard
  [ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".
  ☆50Updated last week
• NJUNLP / ReNeLLM
  The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…
  ☆149Updated 3 months ago