3 papers
cs.LG2026
Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing
Zehao Wang, Lanjun Wang
Large Reasoning Models (LRMs) have demonstrated strong capabilities in generating step-by-step reasoning chains alongside final answers, enabling their deployment in high-stakes do…
cs.LG2026
NK-GAD: Neighbor Knowledge-Enhanced Unsupervised Graph Anomaly Detection
Zehao Wang, Lanjun Wang
Graph anomaly detection aims to identify irregular patterns in graph-structured data. Most unsupervised GNN-based methods rely on the homophily assumption that connected nodes shar…
cs.CR2024
Impart: An Imperceptible and Effective Label-Specific Backdoor Attack
Jingke Zhao, Zan Wang, Yongwei Wang +1
Backdoor attacks have been shown to impose severe threats to real security-critical scenarios. Although previous works can achieve high attack success rates, they either require ac…