3 papers
cs.AI2026
Variation is the Key: A Variation-Based Framework for LLM-Generated Text Detection
Xuecong Li, Xiaohong Li, Qiang Hu +2
Detecting text generated by large language models (LLMs) is crucial but challenging. Existing detectors depend on impractical assumptions, such as white-box settings, or solely rel…
cs.SE2025
FidelityGPT: Correcting Decompilation Distortions with Retrieval Augmented Generation
Zhiping Zhou, Xiaohong Li, Ruitao Feng +5
Decompilation converts machine code into human-readable form, enabling analysis and debugging without source code. However, fidelity issues often degrade the readability and semant…
cs.SE2025
It Only Gets Worse: Revisiting DL-Based Vulnerability Detectors from a Practical Perspective
Yunqian Wang, Xiaohong Li, Yao Zhang +3
With the growing threat of software vulnerabilities, deep learning (DL)-based detectors have gained popularity for vulnerability detection. However, doubts remain regarding their c…