Towards a robust and trustworthy machine learning system development: An engineering perspective

2021/01/31 by Pulei Xiong, Scott Buffett, Shahrear Iqbal +3
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Artificial intelligence #Computer science #Computer security #Data science #Design science #Information and Cyber Security #Knowledge management #Leverage (statistics) #Metamodeling #Robustness (evolution) #Software engineering #Trustworthiness #cs.CR #cs.LG

paper · pdf · doi:10.1016/j.jisa.2022.103121

published as Journal of Information Security and Applications 65 (2022) 103121 · 20 pages (58 pages pre-print), 6 figures

openalex publication_date 2022/02/10 · arxiv created 2022/02/14 · arxiv updated 2022/02/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

While Machine Learning (ML) technologies are widely adopted in many mission critical fields to support intelligent decision-making, concerns remain about system resilience against ML-specific security attacks and privacy breaches as well as the trust that users have in these systems. In this article, we present our recent systematic and comprehensive survey on the state-of-the-art ML robustness and trustworthiness from a security engineering perspective, focusing on the problems in system threat analysis, design and evaluation faced in developing practical machine learning applications, in terms of robustness and user trust. Accordingly, we organize the presentation of this survey intended to facilitate the convey of the body of knowledge from this angle. We then describe a metamodel we created that represents the body of knowledge in a standard and visualized way. We further illustrate how to leverage the metamodel to guide a systematic threat analysis and security design process which extends and scales up the classic process. Finally, we propose the future research directions motivated by our findings. Our work differs itself from the existing surveys by (i) exploring the fundamental principles and best practices to support robust and trustworthy ML system development, and (ii) studying the interplay of robustness and user trust in the context of ML systems. We expect this survey provides a big picture for machine learning security practitioners.

Citations

• Calibrating Noise to Sensitivity in Private Data Analysis
• Explaining and Harnessing Adversarial Examples
• The security of machine learning
• Security Evaluation of Pattern Classifiers under Attack
• Foveation-based Mechanisms Alleviate Adversarial Examples
• Stealing Machine Learning Models via Prediction APIs
• Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
• DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples
• Ensemble Adversarial Training: Attacks and Defenses
• UPSET and ANGRI : Breaking High Performance Image Classifiers
• One pixel attack for fooling deep neural networks
• Scalable Private Learning with PATE
• Certified Defenses against Adversarial Examples
• AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning
• How To Backdoor Federated Learning
• How trust can drive forward the user acceptance to the technology? In-vehicle technology for autonomous vehicle
• On Evaluating Adversarial Robustness
• Strong Black-box Adversarial Attacks on Unsupervised Machine Learning Models
• Deep learning
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Unsupervised Data Augmentation for Consistency Training
• Hacking Neural Networks: A Short Introduction
• Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
• Generalizing from a Few Examples
• Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
• Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning
• Towards the Science of Security and Privacy in Machine Learning