Efficient Code Analysis via Graph Representation Learning-Guided Large Language Models
For software security practitioners, this method enhances malicious code localization in large codebases with reduced annotation costs.
The paper tackles the problem of detecting malicious code fragments spread across multiple files, which LLMs struggle with due to context dilution. The proposed graph-centric pipeline improves detection accuracy, consistently outperforming existing methods on multiple datasets.
Large Language Models (LLMs) have significantly advanced code analysis tasks, yet they struggle to detect malicious behaviors fragmented across files, whose intricate dependencies easily get lost in the vast amount of benign code. We therefore propose a graph-centric attention acquisition pipeline that enhances LLMs' ability to localize malicious behavior. The approach parses a project into a code graph, uses an LLM to encode nodes with semantic and structural signals, and trains a Graph Neural Network (GNN) under sparse supervision. The GNN performs an initial detection, and by interpreting these predictions, identifies key code sections that are most likely to contain malicious behavior. These influential regions are then used to guide the LLM's attention for in-depth analysis. This strategy significantly reduces interference from irrelevant context while maintaining low annotation costs. Extensive experiments show that the method consistently outperforms existing approaches on multiple public and custom datasets, highlighting its potential for practical deployment in software security scenarios.