2 papers
cs.LG2026
Target-Aware Interaction-Guided Reinforcement Learning for Black-Box Node Injection Attacks on Graph Neural Networks
Yi Lan, Ye Yuan
Graph Neural Networks (GNNs) have achieved remarkable performance in graph representation learning, yet their inherent vulnerability to adversarial attacks poses severe security ri…
cs.CR2026
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents
Yuchuan Tian, Mengyu Zheng, Haocheng Mei +5
Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databas…