Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective

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.

20 pages (58 pages pre-print), 6 figures

References in corpus (14)

• Explaining and Harnessing Adversarial Examples
• RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
• Stealing Machine Learning Models via Prediction APIs
• On Evaluating Adversarial Robustness
• Security Evaluation of Pattern Classifiers under Attack
• Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
• Towards the Science of Security and Privacy in Machine Learning
• Data Poisoning Attacks to Deep Learning Based Recommender Systems
• UPSET and ANGRI : Breaking High Performance Image Classifiers
• Discretization based Solutions for Secure Machine Learning against Adversarial Attacks
• A Survey of Game Theoretic Approaches for Adversarial Machine Learning in Cybersecurity Tasks
• Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning
• Strong Black-box Adversarial Attacks on Unsupervised Machine Learning Models
• Hacking Neural Networks: A Short Introduction