Saved in:
Bibliographic Details
Main Authors: Abdelkader, Hala, Abdelrazek, Mohamed, Rani, Priya, Vasa, Rajesh, Schneider, Jean-Guy
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.18292
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909861028036608
author Abdelkader, Hala
Abdelrazek, Mohamed
Rani, Priya
Vasa, Rajesh
Schneider, Jean-Guy
author_facet Abdelkader, Hala
Abdelrazek, Mohamed
Rani, Priya
Vasa, Rajesh
Schneider, Jean-Guy
contents Ensuring robustness in ML-enabled software systems requires addressing critical challenges, such as silent failures, out-of-distribution (OOD) data, and adversarial attacks. Traditional software engineering practices, which rely on predefined logic, are insufficient for ML components that depend on data and probabilistic decision-making. To address these challenges, we propose the ML-On-Rails protocol, a unified framework designed to enhance the robustness and trustworthiness of ML-enabled systems in production. This protocol integrates key safeguards such as OOD detection, adversarial attack detection, input validation, and explainability. It also includes a model-to-software communication framework using HTTP status codes to enhance transparency in reporting model outcomes and errors. To align our approach with real-world challenges, we conducted a practitioner survey, which revealed major robustness issues, gaps in current solutions, and highlighted how a standardised protocol such as ML-On-Rails can improve system robustness. Our findings highlight the need for more support and resources for engineers working with ML systems. Finally, we outline future directions for refining the proposed protocol, leveraging insights from the survey and real-world applications to continually enhance its effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18292
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Ensuring Robustness in ML-enabled Software Systems: A User Survey
Abdelkader, Hala
Abdelrazek, Mohamed
Rani, Priya
Vasa, Rajesh
Schneider, Jean-Guy
Software Engineering
Ensuring robustness in ML-enabled software systems requires addressing critical challenges, such as silent failures, out-of-distribution (OOD) data, and adversarial attacks. Traditional software engineering practices, which rely on predefined logic, are insufficient for ML components that depend on data and probabilistic decision-making. To address these challenges, we propose the ML-On-Rails protocol, a unified framework designed to enhance the robustness and trustworthiness of ML-enabled systems in production. This protocol integrates key safeguards such as OOD detection, adversarial attack detection, input validation, and explainability. It also includes a model-to-software communication framework using HTTP status codes to enhance transparency in reporting model outcomes and errors. To align our approach with real-world challenges, we conducted a practitioner survey, which revealed major robustness issues, gaps in current solutions, and highlighted how a standardised protocol such as ML-On-Rails can improve system robustness. Our findings highlight the need for more support and resources for engineers working with ML systems. Finally, we outline future directions for refining the proposed protocol, leveraging insights from the survey and real-world applications to continually enhance its effectiveness.
title Ensuring Robustness in ML-enabled Software Systems: A User Survey
topic Software Engineering
url https://arxiv.org/abs/2510.18292