English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The advent of the Internet of Things (IoT) has brought forth an era ofunprecedented connectivity, with an estimated 80 billion smart devices expectedto be in operation by the end of 2025. These devices facilitate a multitude ofsmart applications, enhancing the quality of life and efficiency across variousdomains. Machine Learning (ML) serves as a crucial technology, not only foranalyzing IoT-generated data but also for diverse applications within the IoTecosystem. For instance, ML finds utility in IoT device recognition, anomalydetection, and even in uncovering malicious activities. This paper embarks on acomprehensive exploration of the security threats arising from ML's integrationinto various facets of IoT, spanning various attack types including membershipinference, adversarial evasion, reconstruction, property inference, modelextraction, and poisoning attacks. Unlike previous studies, our work offers aholistic perspective, categorizing threats based on criteria such as adversarymodels, attack targets, and key security attributes (confidentiality,availability, and integrity). We delve into the underlying techniques of MLattacks in IoT environment, providing a critical evaluation of their mechanismsand impacts. Furthermore, our research thoroughly assesses 65 libraries, bothauthor-contributed and third-party, evaluating their role in safeguarding modeland data privacy. We emphasize the availability and usability of theselibraries, aiming to arm the community with the necessary tools to bolstertheir defenses against the evolving threat landscape. Through our comprehensivereview and analysis, this paper seeks to contribute to the ongoing discourse onML-based IoT security, offering valuable insights and practical solutions tosecure ML models and data in the rapidly expanding field of artificialintelligence in IoT.

Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them