ai-threat-testing

About ai-threat-testing

Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and supply chain attacks. Integrates with pentest workflows to discover and exploit AI-specific threats.

进攻性人工智能安全测试与利用框架。系统性地针对大型语言模型（LLM）应用检测开放式 Web 应用安全项目（OWASP）LLM 十大风险，包括提示注入、模型提取、数据投毒和供应链攻击。与渗透测试工作流集成，用于发现并利用特有的人工智能威胁。