Saved in:
Bibliographic Details
Main Authors: Vitale, Francesco, Flammini, Francesco, Caporuscio, Mauro, Mazzocca, Nicola
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.10876
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908916619673600
author Vitale, Francesco
Flammini, Francesco
Caporuscio, Mauro
Mazzocca, Nicola
author_facet Vitale, Francesco
Flammini, Francesco
Caporuscio, Mauro
Mazzocca, Nicola
contents Context: Ensuring high levels of dependability in modern computer-based systems has become increasingly challenging due to their complexity. Although systems are validated at design time, their behavior can be different at runtime, possibly showing control-flow anomalies due to ``unknown unknowns''. Objective: We aim to detect control-flow anomalies through software monitoring, which verifies runtime behavior by logging software execution and detecting deviations from expected control flow. Methods: We propose a methodology to develop software monitors for control-flow anomaly detection through Large Language Models (LLMs) and conformance checking. The methodology builds on existing software development practices to maintain traditional V\&V while providing an additional level of robustness and trustworthiness. It leverages LLMs to link design-time models and implementation code, automating source-code instrumentation. The resulting event logs are analyzed via conformance checking, an explainable and effective technique for control-flow anomaly detection. Results: We test the methodology on a case-study scenario from the European Railway Traffic Management System / European Train Control System (ERTMS/ETCS), which is a railway standard for modern interoperable railways. The results obtained from the ERTMS/ETCS case study demonstrate that LLM-based source-code instrumentation can achieve up to 82.849% control-flow coverage of the reference design-time process model, while the subsequent conformance checking-based anomaly detection reaches a peak performance of 95.957% F1-score and 93.669% AUC. Conclusion: Incorporating domain-specific knowledge to guide LLMs in source-code instrumentation significantly allowed obtaining reliable and quality software logs and enabled effective control-flow anomaly detection through conformance checking.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Architecting software monitors for control-flow anomaly detection through large language models and conformance checking
Vitale, Francesco
Flammini, Francesco
Caporuscio, Mauro
Mazzocca, Nicola
Software Engineering
Machine Learning
Context: Ensuring high levels of dependability in modern computer-based systems has become increasingly challenging due to their complexity. Although systems are validated at design time, their behavior can be different at runtime, possibly showing control-flow anomalies due to ``unknown unknowns''. Objective: We aim to detect control-flow anomalies through software monitoring, which verifies runtime behavior by logging software execution and detecting deviations from expected control flow. Methods: We propose a methodology to develop software monitors for control-flow anomaly detection through Large Language Models (LLMs) and conformance checking. The methodology builds on existing software development practices to maintain traditional V\&V while providing an additional level of robustness and trustworthiness. It leverages LLMs to link design-time models and implementation code, automating source-code instrumentation. The resulting event logs are analyzed via conformance checking, an explainable and effective technique for control-flow anomaly detection. Results: We test the methodology on a case-study scenario from the European Railway Traffic Management System / European Train Control System (ERTMS/ETCS), which is a railway standard for modern interoperable railways. The results obtained from the ERTMS/ETCS case study demonstrate that LLM-based source-code instrumentation can achieve up to 82.849% control-flow coverage of the reference design-time process model, while the subsequent conformance checking-based anomaly detection reaches a peak performance of 95.957% F1-score and 93.669% AUC. Conclusion: Incorporating domain-specific knowledge to guide LLMs in source-code instrumentation significantly allowed obtaining reliable and quality software logs and enabled effective control-flow anomaly detection through conformance checking.
title Architecting software monitors for control-flow anomaly detection through large language models and conformance checking
topic Software Engineering
Machine Learning
url https://arxiv.org/abs/2511.10876