Yue Xiao

Reducing False Positives in Provenance-Based Intrusion Detection Systems

OmniVul: A Holistic, Multi-Turn Conversational Benchmark for LLM-Based Vulnerability Assessment

With more than 20,000 Common Vulnerabilities and Exposures (CVEs) reported annually, software vulnerabilities represent a critical cybersecurity challenge. This volume has intensified the demand for automated detection and analysis, motivating the integration of large language models (LLMs) for such tasks. However, exi...

OmniVul: A Holistic, Multi-Turn Conversational Benchmark for LLM-Based Vulnerability Assessment

An evaluation of five state-of-the-art LLMs on OmniVul reveals distinct performance gaps, with top-1 accuracy remaining below 50% on average for vulnerable code detection and CVE identification, demonstrating that current models lack critical reasoning capabilities for reliable vulnerability assessment.