Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
Tian Zhang, Yiwei Xu, Juan Wang +8
Tool-augmented large language model (LLM) agents aggregate dialogue history, tool outputs, and retrieved content into an accumulated runtime state to complete multi-step tasks. Thi…
cs.CR2025
URL2Graph++: Unified Semantic-Structural-Character Learning for Malicious URL Detection
Ye Tian, Yifan Jia, Yanbin Wang +3
Malicious URL detection remains a major challenge in cybersecurity, primarily due to two factors: (1) the exponential growth of the Internet has led to an immense diversity of URLs…