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

📅 2026-08-15
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the degradation in recognition performance and annotation budget allocation challenges caused by concept drift in IoT traffic. We propose an adaptive strategy that decouples annotation volume from sample selection decisions. Specifically, an interpretable consistency-based drift detector is designed to dynamically adjust labeling budgets, while uniform sampling is employed to mitigate retraining bias. Extensive validation on 3.8 million real-world records spanning two years demonstrates that this approach effectively sustains classifier performance under limited budgets. The proposed method significantly outperforms traditional detector-guided selection strategies and achieves performance comparable to confidence-based adaptive methods. Consequently, this work provides an efficient and robust active learning solution for IoT device identification in dynamic environments.
📝 Abstract
Identification of IoT device types from passive traffic is increasingly used for security management in enterprise and ISP networks. However, the performance of machine learning-based classifiers gradually degrades under concept drift as device behavior evolves. Therefore, maintaining classification performance requires periodic retraining with newly labeled deployment traffic. The operational challenge is determining how much and which deployment traffic instances to label for maintaining classification performance. We show that these two decisions should be treated separately. While retraining solely on instances selected by a drift detector is prone to systematically overlooking parts of the emerging behavioral space, uniformly sampled deployment traffic captures more representative behavioral changes. Instead, drift detection is more effective at determining the amount of deployment traffic that should be labeled. We make three contributions. (1) We conduct a two-year longitudinal study of IoT traffic and characterize how behavioral evolution manifests across device classes and how retraining with newly labeled traffic restores classification performance. (2) We develop a conformity-based drift detector that captures class-conditional behavioral models directly from raw traffic features and provides feature-level explanations of behavioral evolution. (3) We demonstrate that adjusting the traffic labeling rate according to the observed behavioral evolution, combined with uniform traffic sampling, maintains classifier performance more effectively than detector-guided sample selection and is beneficial to managing the traffic labeling effort. We further show that this strategy performs comparably to confidence-guided adaptation while providing feature-level explanations. Our evaluation uses 3.8 million IPFIX flow records collected from 21 IoT types over more than 2 years.
Problem

Research questions and friction points this paper is trying to address.

IoT Device Identification
Concept Drift
Budget-Aware Traffic Labeling
Model Maintenance
Innovation

Methods, ideas, or system contributions that make the work stand out.

Concept Drift
Budget-Aware Labeling
Conformity-based Detection
Uniform Sampling
IoT Device Identification
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
S
Shayan Azizi
School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW 2052, Australia
N
Norihiro Okui
KDDI Research, Japan
M
Masataka Nakahara
KDDI Research, Japan
A
Ayumu Kubota
KDDI Research, Japan
G
Gustavo Batista
School of Computer Science and Engineering, University of New South Wales, Sydney, NSW 2052, Australia
H
Hassan Habibi Gharakaheili
School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW 2052, Australia