Unraveling Attacks to Machine-Learning-Based IoT Systems: A Survey and the Open Libraries Behind Them

• Published in: IEEE internet of things journal Vol. 11; no. 11; pp. 19232 - 19255
• Main Authors: Liu, Chao, Chen, Boxi, Shao, Wei, Zhang, Chris, Wong, Kelvin K. L., Zhang, Yi
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.06.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Anomalies; Artificial intelligence; attack; Availability; Cybersecurity; Data models; Data privacy; Feature extraction; Inference; Internet of Things; Internet of Things (IoT); Libraries; Machine learning; machine learning (ML); open library; Security; Training
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2024.3377730

The advent of the Internet of Things (IoT) has brought forth an era of unprecedented connectivity, with an estimated 80 billion smart devices expected to be in operation by the end of 2025. These devices facilitate a multitude of smart applications, enhancing the quality of life and efficiency across various domains. Machine learning (ML) serves as a crucial technology, not only for analyzing IoT-generated data but also for diverse applications within the IoT ecosystem. For instance, ML finds utility in IoT device recognition, anomaly detection, and even in uncovering malicious activities. This article embarks on a comprehensive exploration of the security threats arising from ML's integration into various facets of IoT, spanning various attack types, including membership inference, adversarial evasion, reconstruction, property inference, model extraction, and poisoning attacks. Unlike previous studies, our work offers a holistic perspective, categorizing threats based on criteria, such as adversary models, attack targets, and key security attributes (confidentiality, integrity, and availability). We delve into the underlying techniques of ML attacks in IoT environment, providing a critical evaluation of their mechanisms and impacts. Furthermore, our research thoroughly assesses 65 libraries, both author-contributed and third-party, evaluating their role in safeguarding model and data privacy. We emphasize the availability and usability of these libraries, aiming to arm the community with the necessary tools to bolster their defenses against the evolving threat landscape. Through our comprehensive review and analysis, this article seeks to contribute to the ongoing discourse on ML-based IoT security, offering valuable insights and practical solutions to secure ML models and data in the rapidly expanding field of artificial intelligence in IoT.