Full Text:
<21>
CLC number:
On-line Access: 2025-05-30
Received: 2025-01-16
Revision Accepted: 2025-04-14
Crosschecked: 0000-00-00
Cited: 0
Clicked: 39
LLM-enhanced probabilistic modeling for effective static analysis alarms
| |||||||||||||
Xinlong PAN1,2, Jianhua LI1,2, Zhihong ZHOU1,2, Gaolei LI1,2, Xiuzhen CHEN1,2,Jin MA1,2, Jun WU1,2, Quanhai ZHANG1,2. LLM-enhanced probabilistic modeling for effective static analysis alarms[J]. Frontiers of Information Technology & Electronic Engineering, 1998, -1(-1): .
@article{title="LLM-enhanced probabilistic modeling for effective static analysis alarms",
author="Xinlong PAN1,2, Jianhua LI1,2, Zhihong ZHOU1,2, Gaolei LI1,2, Xiuzhen CHEN1,2,Jin MA1,2, Jun WU1,2, Quanhai ZHANG1,2",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2500038"
}
%0 Journal Article
%T LLM-enhanced probabilistic modeling for effective static analysis alarms
%A Xinlong PAN1
%A 2
%A Jianhua LI1
%A 2
%A Zhihong ZHOU1
%A 2
%A Gaolei LI1
%A 2
%A Xiuzhen CHEN1
%A 2
%A Jin MA1
%A 2
%A Jun WU1
%A 2
%A Quanhai ZHANG1
%A 2
%J Journal of Zhejiang University SCIENCE C
%V -1
%N -1
%P
%@ 2095-9184
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2500038
TY - JOUR
T1 - LLM-enhanced probabilistic modeling for effective static analysis alarms
A1 - Xinlong PAN1
A1 - 2
A1 - Jianhua LI1
A1 - 2
A1 - Zhihong ZHOU1
A1 - 2
A1 - Gaolei LI1
A1 - 2
A1 - Xiuzhen CHEN1
A1 - 2
A1 - Jin MA1
A1 - 2
A1 - Jun WU1
A1 - 2
A1 - Quanhai ZHANG1
A1 - 2
J0 - Journal of Zhejiang University Science C
VL - -1
IS - -1
SP -
EP -
%@ 2095-9184
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2500038
Abstract: static analysis presents significant challenges in alarm handling, where probabilistic models and alarm prioritization are essential methods for addressing these issues. These models prioritize alarms based on user feedback, thereby alleviating the burden on users to manually inspect alarms. However, they often encounter limitations related to efficiency and issues such as false generalization. While learning-based approaches have demonstrated promise, they typically incur high training costs and are constrained by the predefined structures of existing models. Moreover, the integration of large language models (LLMs) in static analysis has yet to reach its full potential, often resulting in lower accuracy rates in vulnerability identification.To tackle these challenges, we introduce BINLLM, a novel framework that harnesses the generalization capabilities of LLMs to enhance alarm probability models through rule learning. Our approach integrates LLM-derived abstract rules into the probabilistic model, utilizing alarm paths and critical statements from static analysis. This integration enhances the models reasoning capabilities, improving its effectiveness in prioritizing genuine bugs while mitigating false generalizations. We evaluated BINLLM on a suite of C programs and observed 40.1% and 9.4% reduction in the number of checks required for alarm verification compared to two state-of-the-art baselines, underscoring the potential of combining LLMs with static analysis to improve alarm management.
Open peer comments: Debate/Discuss/Question/Opinion
<1>