Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents
Junliang Liu, Ruoyu Li, Wenxin Tang +4
LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progressive-disclosure design expose…
cs.CR2026
DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization
Wenxin Tang, Wenbin Li, Junliang Liu +10
Software vulnerability detection plays a critical role in ensuring system security, where real-world auditing requires not only determining whether a function is vulnerable but als…