2 papers
cs.HC2026
"You do understand that people don't trust technology?": Explaining Trusted Execution Environments to Non-Experts
McKenna McCall, Carolina Carreira, Miguel Flores +1
Trusted Execution Environments (TEEs) protect confidentiality and integrity of trusted applications by creating an isolated environment for executing code. Prior work has shown tha…
cs.CR2025
RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
Peter Yong Zhong, Siyuan Chen, Ruiqi Wang +4
Tool-Based Agent Systems (TBAS) allow Language Models (LMs) to use external tools for tasks beyond their standalone capabilities, such as searching websites, booking flights, or ma…