ai-kill-chain

Extended Cyber Kill Chain for AI-Era Threats تحديث لسلسلة القتل السيبراني من Lockheed Martin لصالح المدافعين الذين يتعاملون مع هجمات LLM والوكلاء الأذكياء agentic AI. يضيف مرحلة ما قبل الهجوم لاختراق سلسلة توريد النماذج. يضيف تقنيات فرعية خاصة بالذكاء الاصطناعي إلى كل مرحلة من المراحل السبع...

exploit-notes

🎯 Pentest Playbook Index Welcome to the comprehensive penetra...

Indirect Prompt Injection Attacks Against LLM Assistants

Really good research on practical attacks against LLM agents. "Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous" Abstract: The growing integration of LLMs into applications has introduced new security risks, notably known as...

Akamai Firewall for AI: Get Powerful Protection for New LLM App Threats

Protect against LLM attacks such as prompt injection, exfiltration and extraction, and toxic AI outputs with Akamai Firewall for AI...