Compressed Network in Network Models for Traffic Classification

Lu, Manli; Zhou, Bin; Bu, Zhiyong; Zhang, Kecheng; Ling, Zhen-Hua

doi:10.1109/wcnc49053.2021.9417340

Cited by 6 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other approaches include model optimization using compression techniques [24]. In [43], Lu et al propose a compressed Network In Network (NIN) model for TC. They design a step-wise pruning and Knowledge Distillation (KD) strategy to train the compressed model, aiming to reduce storage and computing resources.…”

Section: Optimized Dnn For Tcmentioning

confidence: 99%

“…The NIN basic architecture is optimized in a follow-up work using self-distillation and KD for TC [44]. The model is further optimized with pruning to remove redundant filters and employs knowledge distillation to train compressed models without compromising performance.…”

Section: Optimized Dnn For Tcmentioning

confidence: 99%

“…In STL and MTL approaches for TC, most of the architectures are not optimized to run on constrained devices, except very recent state-of-the-art TC based on transformer architectures with attention mechanisms [40] or DNN compression [44] but with no results on their performance on actual hardware. Our approach exploits recent advances in DNN optimization to achieve such a goal.…”

Section: Research Gaps and Position Of This Work In The Literaturementioning

confidence: 99%

See 2 more Smart Citations

Resource-Efficient Spectrum-Based Traffic Classification on Constrained Devices

Góez,

Aycan Beyazit,

Fletscher

et al. 2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Traffic Classification (TC) systems are designed to identify the applications generating network traffic. Recent advancements in TC leverage Deep Learning (DL) techniques, surpassing traditional methods in complex scenarios, including those with encrypted traffic. Notably, state-of-the-art DL-based TC systems have been developed for wireless networks using Physical Layer (L1) packets. This approach overcomes the common limitation in TC research that assumes traffic flows within a wired network under a single network management domain. Despite their benefits, DL-based TC systems often demand significant computational resources, typically available only in cloud environments. Consequently, deploying models at the edge is often infeasible due to their resource-intensive nature, given their original training and optimization for high-resource environments. The inherent challenge lies in adapting these systems for edge computing scenarios, including deployment at access points. In this paper, we propose a novel methodology that exploits expert knowledge in combination with recent advances in Multi-Task Learning (MTL) and Deep Neural Network (DNN) optimization to allow spectrum-based TC systems to run on constrained devices. Performance evaluations on an NVIDIA Jetson TX2 demonstrate that our most optimized MTL model, handling four TC tasks, can reduce memory requirements by a factor of 2.65x and improve execution time by 3.6x compared to sequential execution of four Single-Task Learning (STL) models in a servergrade configuration, with minimal accuracy impact (less than a 0.5% drop) and energy efficiency of 0.97 millijoules per sample at inference. Compared to other edge platforms such as the Raspberry Pi model 3B+ (RPI3B+) with a low-power Artificial Intelligence (AI)-accelerator such as the Coral Tensor Processing Unit (TPU), the NVIDIA Jetson achieves a 12-fold improvement in energy efficiency with no impact on accuracy. These are the first available results to provide a benchmark for different performance metrics (memory, computing, energy) over heterogeneous constrained devices for this type of TC system.

show abstract

Section: Optimized Dnn For Tcmentioning

confidence: 99%

Section: Optimized Dnn For Tcmentioning

confidence: 99%

Section: Research Gaps and Position Of This Work In The Literaturementioning

confidence: 99%

See 1 more Smart Citation

Resource-Efficient Spectrum-Based Traffic Classification on Constrained Devices

Góez,

Aycan Beyazit,

Fletscher

et al. 2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…In addition, the protocol profiling method and automatic rule extraction method are suggested in the study. Later on, Lu, et al [30] proposed a network-in-network (NIN) model to reduce the need for computing and storage resources. Gradual pruning and knowledge distillation (KD) compression were used to train the model.…”

Section: Related Workmentioning

confidence: 99%

RFSE-GRU: Data Balanced Classification Model for Mobile Encrypted Traffic in Big Data Environment

Dener

2023

IEEE Access

View full text Add to dashboard Cite

With the widespread use of mobile technologies and the Internet, traffic in mobile networks is increasing. This situation has made the classification of traffic an important element for data security and network management. However, encryption of traffic in modern networks makes it difficult to classify traffic with traditional methods. In this study, a unique deep learning-based classification model is proposed for the classification of encrypted mobile traffic data. The proposed model is a classification model called RFSE-GRU, which combines the Gated Recurrent Units (GRU) algorithm, feature selection and data balancing. The features that are more meaningful in the classification process are determined by selecting the features with the Random Forest algorithm. In addition, Synthetic Minority Oversampling Technique (SMOTE) oversampling algorithm and Edited Nearest Neighbor (ENN) undersampling algorithm were used together to reduce the negative impact of data imbalance on classification performance. The study was carried out on Apache Spark big data platform in Google Colab environment. In the study, ISCX VPN-Non VPN and UTMobileNet2021 datasets were used. Binary and multiclass classifications were made for the ISCX VPN-Non VPN dataset, and multiclass classifications were made for the UTMobileNet2021 dataset by using various algorithms on the datasets. The proposed model has been compared with eleven different algorithms and hybrid methods. At the same time, the effect of data balancing and feature selection on classification performance is examined. As a result, the proposed model achieved 93.91%, 82.68% and 96.83% accuracy rates in ISCX VPN-Non VPN binary and multiclass, UTMobileNet2021 multiclass classifications, respectively.

show abstract

A Systematic Review: Imbalanced Network Traffic Classification Using Machine Learning Techniques

Kaur

Virk

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Compressed Network in Network Models for Traffic Classification

Cited by 6 publications

References 12 publications

Resource-Efficient Spectrum-Based Traffic Classification on Constrained Devices

Resource-Efficient Spectrum-Based Traffic Classification on Constrained Devices

RFSE-GRU: Data Balanced Classification Model for Mobile Encrypted Traffic in Big Data Environment

A Systematic Review: Imbalanced Network Traffic Classification Using Machine Learning Techniques

Contact Info

Product

Resources

About