24시간 내 취약점 보고 의무화를 위한 AI-Native Security 설계
EU Cyber Resilience Act: What AI Developers Need to Know for CRA Compliance
EU Cyber Resilience Act: What AI Developers Need to Know for CRA Compliance
Security researchers tricked LLMs into giving them cocaine recipes by abusing role models for prompt injection
Want AI Agents That Don't Spill Secrets? Don't Give Them Secrets
LLM Token 경계 붕괴로 인한 Promptware Kill Chain 분석 및 Zero Trust 대응 전략
Claude Opus 4.6 기반 AI 에이전트의 6,000건 Prompt Injection 방어 성공
OpenAI: Yoo-hoo, look over here, we do that security stuff too!
Defender flujos de agentes contra el OWASP LLM Top 10
Your agent takes orders from the web pages it reads
Securing LLM Agent Teams: Inside NRT-Defense v0.4.0
I tested 5 LLMs for prompt-injection leaks. Same code, 0% to 90%.
MCP Security Crisis: Two Open-Source Frameworks Solving the Agent Security Problem
I shipped 35 bugs in my AI chatbot. The scariest one was on the output side.
I built a WordPress AI chatbot where the free tier isn't a trial. Here's the design story.
How to Secure Local LLM Model Files: A Zero Trust Guide
과잉 설정된 Keyword 기반 가드레일로 인한 Fable 모델의 런타임 Fallback 이슈
Prompt Injection 로그 삽입을 통한 Agentic Coding 보안 취약성 증명
The Agent Revolution Is Here and It's Messy
I Fuzzed 12 LLMs With 19 Payloads — Here What Broke
AI Code Security: Claude's rsync Bugs; Europe's GNSS Interference & GPS Anomalies
What bothered me about the new SafeBreach Gemini paper wasn't the exploit