Automated detection of atomicity violations in large-scale systems

2025-04-01

AI Summary

To address the challenge of detecting atomicity violations caused by asynchronous interrupts in interrupt-driven critical systems, this paper proposes a novel framework integrating static analysis with a multi-agent large language model (LLM) architecture. A domain-expert agent identifies potential violation patterns, while a judge agent performs formal verification by combining program slicing and operational dependency modeling, augmented with domain-specific knowledge to enhance precision. The approach balances scalability over large state spaces with semantic fidelity to domain constraints. Evaluated on RaceBench 2.1, SV-COMP, and RWIP benchmarks, it achieves 92.3% precision and 86.6% recall, with F1-scores improving by 27.4–118.2% over state-of-the-art methods. This work represents the first deep integration of LLM agents and static analysis for atomicity verification in interrupt-driven systems.

Technology Category

• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Security and Privacy: Large-scale security measurements

Abstract

Atomicity violations in interrupt-driven programs pose a significant threat to software safety in critical systems. These violations occur when the execution sequence of operations on shared resources is disrupted by asynchronous interrupts. Detecting atomicity violations is challenging due to the vast program state space, application-level code dependencies, and complex domain-specific knowledge. We propose Clover, a hybrid framework that integrates static analysis with large language model (LLM) agents to detect atomicity violations in real-world programs. Clover first performs static analysis to extract critical code snippets and operation information. It then initiates a multi-agent process, where the expert agent leverages domain-specific knowledge to detect atomicity violations, which are subsequently validated by the judge agent. Evaluations on RaceBench 2.1, SV-COMP, and RWIP demonstrate that Clover achieves a precision/recall of 92.3%/86.6%, outperforming existing approaches by 27.4-118.2% on F1-score.

Problem

• Detecting atomicity violations in interrupt-driven programs
• Overcoming vast state space and code dependencies
• Improving precision and recall in violation detection

Innovation

• Hybrid framework combining static analysis and LLM agents
• Multi-agent process for detecting atomicity violations
• Domain-specific expert agent validates violations