Oct 2026· Proceedings of the ACM on Software Engineering· Vol 3, pp. 2996 - 3020· 0 citations· 128 references
TL;DR
This work proposes a novel neuro-symbolic approach to static analysis, named ELSA, which comprises two key modules, namely, LLM-assisted static analysis and analyzer ensemble (the ensemble of multiple LLM-assisted static analyzers), each incorporating two distinct strategies.
Abstract
Smart contracts facilitate and enforce agreements between untrusted parties without trusted intermediaries, but vulnerabilities within contracts can cause severe damage once exploited. Various analysis techniques have been proposed for vulnerability detection, but they are typically limited to specific vulnerability types. While recent frameworks employ aggregation to broaden detection capacity, they often accumulate false positives due to loose integration that fails to resolve underlying conflicts. Meanwhile, the semantic reasoning capacity of large language models (LLMs) has shown promise in detecting vulnerabilities, despite inherent reasoning bottlenecks and hallucinations. Recognizing these challenges, in this work, we propose a novel neuro-symbolic approach, named Ensemble LLM-Assisted Static Analysis (ELSA). ELSA comprises two key modules, namely, LLM-assisted static analysis and analyzer ensemble (the ensemble of multiple LLM-assisted static analyzers), each incorporating two distinct strategies. The LLM-assisted static analysis augments individual analysis techniques with constraint-guided neural semantic reasoning, while the analyzer ensemble resolves conflicting outputs to distill a robust consensus. We evaluate ELSA on a comprehensive benchmark, including three open-source datasets and additional self-constructed Zero-Knowledge Proof-based smart contracts whose complexity poses unique challenges to static analysis. Experimental results demonstrate that our approach achieves an overall improvement of at least 17% over baselines and advanced mainstream approaches, effectively bridging semantic gaps and synergizing the complementary advantages of different analyzers. Furthermore, an ablation study and fine-grained analysis are conducted to investigate the key factors contributing to overall performance gains.
Automated vulnerability detection in C source code is a long-standing challenge, as traditional static analysis tools often trade precision for scalability and struggle with complex vulnerability patterns. Recently, large language models (LLMs) have shown promising results; yet, most approaches rely on a single code re...
Francesco C. Grasso, Pietro Liguori, R. Natella et al.· 0 citations
A unified framework combining a novel Hierarchical Cross-Attention Subgraph Neural Network for detection with Large Language Models for explanation form a comprehensive framework that significantly enhances both the technical accuracy and operational usability of smart contract analysis.
Smart contracts control digital assets under conditions of immutability in blockchain networks, making vulnerability detection an important task in decentralized systems security. Traditional static analysis tools generally rely on specific syntactic patterns, which can make it difficult for developers to interpret the...
Cleidimar L. dos Passos, Josué N. Campos, L. M. S. de Carvalho et al.· Brazilian Symposium on Syste...· 0 citations
HSF-Vul is proposed, a novel approach for software vulnerability detection and localization based on hierarchical semantic fusion that frame vulnerability detection as a binary classification task and extend it to line-level localization by analyzing the contribution of individual code lines.
Hong-Tao Wang, Xin Yang, Xiao-Feng Liu et al.· International Conference on...· 0 citations
EADC, a novel advanced evaluation benchmark of LLMs based on an AI compliance knowledge graph and AI compliance legal experts, is introduced, offering a rigorous, AI laws and regulations-aligned benchmark to safeguard high-level and deep compliance in the application of LLMs.
Yan Zhang, Rui-En Li, Yao-Yao Peng et al.· arXiv.org· 0 citations
The exponential growth in software vulnerabilities has created an urgent demand for automated vulnerability detection solutions. Recent research has emphasized the importance of repository-level context for vulnerability detection and has leveraged large language models (LLMs) to address this challenge. Although these...
Xin-Jie Wen, Han-Yue Luo, Cui-Yun Gao et al.· Proceedings of the 41st IEEE...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.