arXiv Machine Learning By Shayan Azizi, Norihiro Okui, Masataka Nakahara, Ayumu Kubota, Gustavo Batista, Hassan Habibi Gharakaheili

Maintaining IoT Device Identification under Concept Drift via Budget-Aware Traffic Labeling

Read the original on arXiv Machine Learning →

arXiv:2608. 15465v1 Announce Type: cross Abstract: Identification of IoT device types from passive traffic is increasingly used for security management in enterprise and ISP networks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI
Aug 20

Performance Drift Detection in Machine Learning as a Service (MLaaS) for IoT Environments

The paper introduces a framework for detecting performance drift in Machine Learning as a Service (MLaaS) tailored to Internet of Things (IoT) settings. It first builds an extraction model that learns the service’s behavior from input‑output pairs, then uses this to jointly monitor changes in data and service behavior. An adaptive temporal mechanism adjusts monitoring frequency, and experiments on real datasets show significant accuracy gains and reduced miss‑detection rates compared to baseline methods.

By Deepak Kanneganti, Sajib Mistry, Sheik Mohammad Mostakim Fattah, Erik Elmroth, Aneesh Krishna, Monowar Bhuyan
arXiv Machine Learning
Jul 20

Label-Free Concept Drift Assessment for Reliable AI in Emerging Wireless Applications

arXiv:2508. 00042v2 Announce Type: replace-cross Abstract: Machine learning models deployed in non-stationary environments degrade silently, since as the input distribution drifts their accuracy decays without an error signal and without labels to reveal it.

By Athanasios Tziouvaras, Carolina Fortuna, George Floros, Kostas Kolomvatsos, Panagiotis Sarigiannidis, Marko Grobelnik, Bla\v{z} Bertalani\v{c}