microsoft / SecRLLinks
Benchmarking LLM agents on Cyber Threat Investigation.
☆109Updated this week
Alternatives and similar repositories for SecRL
Users that are interested in SecRL are comparing it to the libraries listed below
Sorting:
- Agentic Workflows Made Simple☆160Updated 10 months ago
- ☆55Updated 8 months ago
- Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models☆92Updated this week
- Curated list of Open Source project focused on LLM security☆69Updated 3 weeks ago
- ☆66Updated last year
- NOVA: The Prompt Pattern Matching☆63Updated 2 months ago
- ☆44Updated last year
- A knowledge source about TTPs used to target GenAI-based systems, copilots and agents☆132Updated 3 weeks ago
- ☆127Updated last week
- AI Security Shared Responsibility Model☆87Updated 3 months ago
- ☆355Updated 3 months ago
- Top 10 for Agentic AI (AI Agent Security) serves as the core for OWASP and CSA Red teaming work☆162Updated 3 months ago
- ☆57Updated 3 weeks ago
- Reference notes for Attacking and Defending Generative AI presentation☆69Updated last year
- ☆422Updated this week
- Proximity is a MCP security scanner powered with NOVA☆269Updated 3 months ago
- A powerful tool that leverages AI to automatically generate comprehensive security documentation for your projects☆99Updated 3 months ago
- Threat model for Azure Storage - Library of all the attack scenarios on Azure Storage, and how to mitigate them following a risk-based ap…☆59Updated 2 years ago
- 🤖 A GitHub action that leverages fabric patterns through an agent-based approach☆32Updated last year
- HoneyAgents is a PoC demo of an AI-driven system that combines honeypots with autonomous AI agents to detect and mitigate cyber threats. …☆58Updated 2 years ago
- Red Teaming for AI and Cloud☆203Updated last month
- Vulnerability impact analyzer that reduces false positives in SCA tools by performing intelligent code analysis. Uses agentic AI with ope…☆62Updated 10 months ago
- ATLAS tactics, techniques, and case studies data☆96Updated 3 weeks ago
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks☆93Updated 7 months ago
- ☆72Updated last month
- An open-source knowledge base of defensive countermeasures to protect AI/ML systems. Features interactive views and maps defenses to know…☆116Updated last week
- A comprehensive GenAI protection system designed to protect against malicious prompts, injection attacks, and harmful content. System inc…☆95Updated 3 months ago
- A Caldera plugin for the emulation of complete, realistic cyberattack chains.☆60Updated last month
- 🛡️ SIGMA Detection Engineering Platform A comprehensive AI-powered detection engineering platform for security teams to explore MITRE AT…☆46Updated 6 months ago
- source code for the offsecml framework☆44Updated last year