collaborators

7 papers

cs.CR2026

Securing LLM Agents Need Intent-to-Execution Integrity

Wenjie Qu, Ming Xu, Peiran Wang +3

This position paper argues that securing LLM agents requires first defining an end-to-end correctness property that specifies when an agent's execution faithfully reflects the user…

cs.CR2026

ARuleCon: Agentic Security Rule Conversion

Ming Xu, Hongtai Wang, Yanpei Guo +5

Security Information and Event Management (SIEM) systems make it possible for detecting intrusion anomalies in real-time manner by their applied security rules. However, the hetero…

cs.CR2026

IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation

Yanpei Guo, Wenjie Qu, Linyu Wu +7

Commercial large language models are typically deployed as black-box API services, requiring users to trust providers to execute inference correctly and report token usage honestly…

cs.CR2025

ThreatPilot: Attack-Driven Threat Intelligence Extraction

Ming Xu, Hongtai Wang, Jiahao Liu +6

Efficient defense against dynamically evolving advanced persistent threats (APT) requires the structured threat intelligence feeds, such as techniques used. However, existing threa…

cs.CR2025

RulePilot: An LLM-Powered Agent for Security Rule Generation

Hongtai Wang, Ming Xu, Yanpei Guo +3

The real-time demand for system security leads to the detection rules becoming an integral part of the intrusion detection life-cycle. Rule-based detection often identifies malicio…

cs.CR2025

MoPE: A Mixture of Password Experts for Improving Password Guessing

Mingjian Duan, Ming Xu, Shenghao Zhang +2

Textual passwords remain a predominant authentication mechanism in web security. To evaluate their strength, existing research has proposed several data-driven models across variou…