3 papers
cs.CR2026
MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory Learning
Changyue Jiang, Jiayi Wang, Xin Wen +3
Mobile agents powered by foundation models now automate complex, multi-step workflows on real devices, but their trajectories can violate app-specific security policies. Existing t…
cs.AR2026
HierSVA: A Data Synthesis Pipeline, Dataset, and Benchmark for LLM-Driven Hierarchical Hardware Formal Verification
Maohua Nie, Jiang Zhu, Jingqun Zhang +5
We present HierSVA, an integrated suite that combines a pipeline, dataset, and benchmark for LLM-driven hierarchical hardware formal verification. HierSVA-SP pairs an RTL preproces…
cs.CL2025
ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models
Changyi Li, Jiayi Wang, Xudong Pan +2
Large Reasoning Models (LRMs) leverage explicit reasoning traces, known as Chain-of-Thought (CoT) reasoning, to decompose complex problems into intermediate steps before deriving f…