Alternatives and similar repositories for ASTRAL

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

• uiuc-kang-lab / InjecAgent
  ☆63Updated 11 months ago
• AIM-Intelligence / Automated-Multi-Turn-Jailbreaks
  ☆71Updated 6 months ago
• LostOxygen / llm-confidentiality
  Whispers in the Machine: Confidentiality in Agentic Systems
  ☆37Updated 2 weeks ago
• thu-coai / Agent-SafetyBench
  ☆32Updated 3 weeks ago
• thu-coai / Backdoor-Data-Extraction
  ☆20Updated 2 weeks ago
• theshi-1128 / ABJ-Attack
  LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
  ☆20Updated last week
• xirui-li / DrAttack
  Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
  ☆52Updated 9 months ago
• ThuCCSLab / JailbreakEval
  [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.
  ☆158Updated 2 months ago
• HumanCompatibleAI / tensor-trust
  A prompt injection game to collect data for robust ML research
  ☆61Updated 4 months ago
• llm-platform-security / SecGPT
  An Execution Isolation Architecture for LLM-Based Agentic Systems
  ☆80Updated 4 months ago
• declare-lab / ferret
  Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
  ☆16Updated 9 months ago
• leondz / lm_risk_cards
  Risks and targets for assessing LLMs & LLM vulnerabilities
  ☆30Updated last year
• CS-EVAL / CS-Eval
  CS-Eval is a comprehensive evaluation suite for fundamental cybersecurity models or large language models' cybersecurity ability.
  ☆43Updated 6 months ago
• dukeceicenter / jailbreak-reasoning-openai-o1o3-deepseek-r1
  ☆80Updated last month
• facebookresearch / SecAlign
  Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"
  ☆48Updated 2 months ago
• Babelscape / ALERT
  Official repository for the paper "ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming"
  ☆42Updated 8 months ago
• SALT-NLP / PopupAttack
  Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups
  ☆32Updated 5 months ago
• sail-sg / Agent-Smith
  [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
  ☆101Updated last year
• agiresearch / ASB
  Agent Security Bench (ASB)
  ☆81Updated last month
• briland / LLM-security-and-privacy
  LLM security and privacy
  ☆49Updated 7 months ago
• poloclub / llm-self-defense
  LLM Self Defense: By Self Examination, LLMs know they are being tricked
  ☆34Updated last year
• PKU-YuanGroup / Hallucination-Attack
  Attack to induce LLMs within hallucinations
  ☆154Updated last year
• Aatrox103 / SAP
  ☆45Updated last year
• usail-hkust / JailTrickBench
  Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)
  ☆135Updated 6 months ago
• XuandongZhao / weak-to-strong
  [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models
  ☆76Updated last month
• pasquini-dario / LLMmap
  ☆40Updated 8 months ago
• RobustNLP / DeRTa
  A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.
  ☆60Updated 2 weeks ago
• Lordog / R-Judge
  R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)
  ☆76Updated 3 weeks ago
• liu00222 / Open-Prompt-Injection
  This repository provides a benchmark for prompt Injection attacks and defenses
  ☆216Updated this week
• controllability / jailbreak-evaluation
  The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation.
  ☆23Updated 7 months ago