Research Notes
Deep dives into computer science research — systems, security, AI/ML, and beyond
- Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
- Formalizing and Benchmarking Prompt Injection Attacks and Defenses
- ISOLATEGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection