مصادر أمن الذكاء الاصطناعي
أكثر من 71 أداة ومختبر وشهادة ومجتمع منتقاة لأمن الـ LLM والـ prompt injection والـ AI red teaming.
The labs, modules and Gauntlet are aligned to the OWASP Top 10 for LLM Applications and the OWASP Top 10 for Agentic Applications 2026. Both are worth reading before working through the tools below.
39 open-source and commercial tools for LLM security testing, including garak, promptfoo, Microsoft PyRIT, and NVIDIA NeMo Guardrails
7 hands-on practice environments for AI red teaming and prompt injection, with difficulty ratings from beginner to advanced
7 professional certifications for AI security practitioners, including OSAI+, CAISP, HTB COAE, and GAISP from recognized industry bodies
18 forums, researcher networks, newsletters, and open-source projects tracking AI threats and sharing defense strategies
OffSec's AI red teaming certification covering adversarial testing of LLM and AI systems.
Hack The Box certification focused on offensive AI techniques and adversarial machine learning.
أرسل لنا رسالة باسم المصدر ورابطه، ونحن نراجع كل اقتراح.