PPL
Chen
Papers (4)
PrivScope: Task-scoped Disclosure Control for Hybrid Agentic SystemsRealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior ImitationRealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior ImitationIPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection