OWASP ASI06 대응을 위한 Agent Memory Guard 설계 및 200개 이상의 벤치마크 검증
How I Built an OWASP Memory Guard for AI Agents (ASI06)
Scan-before-write 패턴을 통한 LangGraph Memory Poisoning(ASI06) 원천 차단
Securing LangGraph Multi-Agent Workflows Against Memory Poisoning (ASI06)
Pydantic Validator 기반 ASI06 Memory Poisoning 원천 차단 아키텍처
Securing OpenAI Agents SDK Against Memory Poisoning (ASI06) Using Pydantic Field Validators
Stateless Prompt Injection에서 Stateful Memory Poisoning으로의 공격 패러다임 전환
Prompt Injection Was Stateless. Memory Poisoning Is Persistence
Claude Code의 Memory Architecture 분석 및 보안 결함 해결을 통한 ShieldCortex 구현
We Studied Claude Code's Source. Here's How Anthropic's AI Actually Remembers — And Why It's Broken.