llm-vulnerabilities 开源项目推荐（11 个）

msoedov /agentic_security

代理式 LLM 漏洞扫描器 / AI 红队测试工具包

requie /LLMSecurityGuide

大型语言模型（LLMs）安全保护的综合参考资料。涵盖OWASP生成式AI十大风险、即时注入、对抗性攻击、现实世界事件及实用防御。包含红队工具、防护措施和缓解策略目录，帮助开发者、研究人员和安全团队负责任地部署人工智能。

briland /LLM-security-and-privacy

LLM security and privacy

TrustAI-laboratory /LMAP

LMAP (large language model mapper) is like NMAP for LLM, is an LLM Vulnerability Scanner and Zero-day Vulnerability Fuzzer.

ridpath /llm-vuln-scanner

Security scanner for local LLMs scanning LLM vulnerabilities including jailbreaks, prompt injection, training data leakage, and adversarial abuse

ParraX123 /meta-ai-bug-bounty

🛡️ Discover and analyze critical vulnerabilities in Meta AI's Instagram Group Chat, ensuring robust security through comprehensive testing and reporting.

minuva /fast-prompt-attack-detect

User prompt attack detection system

donbaudin /meta-ai-bug-bounty

Bug bounty report demonstrating prompt injection and command execution vulnerabilities in Meta AI's Instagram Group Chat

usrtem /AI-Cybersecurity-Research

White-paper & talk covering benefits, risks, and mitigation frameworks for AI and LLMs in cybersecurity (NIST AI RMF, OWASP Top 10 for LLMs, MITRE ATLAS, real-world case studies)

roynaldo1234 /meta-ai-bug-bounty

Meta AI Bug Bounty focuses on vulnerabilities in Instagram's Group Chat feature, revealing critical security risks. Join us in improving AI safety and explore our findings on GitHub! 🐙✨

Gothgirl0 /ai-agent-team

🤖 Elevate content creation and analysis with AI Agent Team, featuring six professional AI agents for enhanced collaboration and quality.