Research Notes

Research Notes

Deep dives into computer science research — systems, security, AI/ML, and beyond

    2026

    • Mar 27 Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
    • Mar 27 Formalizing and Benchmarking Prompt Injection Attacks and Defenses
    • Mar 27 ISOLATEGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems
    • Mar 27 Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
  • Beomsu Lee
  • beomsu317@gmail.com