New HARP framework prioritizes CVEs using adaptive preference fusion

Researchers have developed HARP, a novel framework for prioritizing Common Vulnerabilities and Exposures (CVEs) based on user preferences. Unlike existing systems that assume fixed criteria, HARP adapts to implicit operational preferences by using historical labeled examples. The framework leverages a vulnerability knowledge graph and multiple scoring views (global, enterprise, user) to rank CVE candidates from natural-language queries. Experiments demonstrate HARP's effectiveness across various preference scenarios and LLM backbones, outperforming existing baselines. AI

IMPACT This framework could improve the efficiency and accuracy of cybersecurity threat assessment by better aligning vulnerability prioritization with specific organizational needs.

RANK_REASON The cluster contains a research paper detailing a new framework for vulnerability prioritization. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv cs.CL →

• arXiv

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →