3 papers
cs.CR2026
Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection
Darren Cheng, Wen-Kwang Tsao
Prompt injection remains one of the most practical attack vectors against LLM-integrated applications. We replicate the Microsoft LLMail-Inject benchmark (Greshake et al., 2024) ag…
cs.AI2025
Mapping Smarter, Not Harder: A Test-Time Reinforcement Learning Agent That Improves Without Labels or Model Updates
Wen-Kwang Tsao, Yao-Ching Yu, Chien-Ming Huang
The Enterprise Intelligence Platform must integrate logs from numerous third-party vendors in order to perform various downstream tasks. However, vendor documentation is often unav…
cs.CR2025
Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training
Yao-Ching Yu, Tsun-Han Chiang, Cheng-Wei Tsai +2
Large Language Models (LLMs) have shown remarkable advancements in specialized fields such as finance, law, and medicine. However, in cybersecurity, we have noticed a lack of open-…