4.8 Article

Two-Stage Distillation-Aware Compressed Models for Traffic Classification

Journal

IEEE INTERNET OF THINGS JOURNAL
Volume 10, Issue 16, Pages 14152-14166

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2023.3263487

Keywords

Deep learning (DL); Internet of Things (IoT); knowledge distillation; model compression; self-distillation; traffic classification

Ask authors/readers for more resources

To address the challenges in traffic classification for IoT, we propose lightweight but accurate models that can achieve high accuracy, handle imbalanced traffic, and reduce computation overhead. By utilizing a network-in-network basic model, self-distilled response, feature map, and similarity among traffic types, we achieve compressed architectures without compromising performance. Experimental results demonstrate the efficiency of the proposed compressed model compared to state-of-the-art deep packet models.
Traffic classification is indispensable for the Internet of Things (IoT) in intrusion detection and resource management. Deep-learning (DL)-based strategies are the key tools for traffic classification due to high accuracy but still have some challenges: 1) it is hard to deploy complex DL models on resource-constraint IoT devices and 2) performance is limited because of the ignorance of the similarity between IoT traffic. To address these issues, we propose lightweight but accurate models for traffic classification. First, we adopt a network-in-network basic model to reduce model size. Second, the basic model is trained with self-distilled response, feature map, and similarity among traffic types to enable its identification accuracy. Next, redundant filters are removed from the basic model to achieve compressed architectures. Then, a teacher model updating scheme with knowledge distillation is proposed to train compressed models without compromising performance. Experimental results demonstrate that compared to the state-of-the-art deep packet model, the compressed model can achieve the highest accuracy, deal with imbalanced traffic, and reduce nearly 99% of computation overhead in two encrypted traffic classification scenarios, thus, emphasizing its efficiency.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available