FastTraffic: A lightweight method for encrypted traffic fast classification

Xu, Yuwei; Cao, Jie; Song, Kehui; Xiang, Qiao; Cheng, Guang

doi:10.1016/j.comnet.2023.109965

Cited by 5 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, maintaining the same experimental environment and dataset is crucial for a fair comparison. Since it is difficult to reproduce these conditions exactly, we compare our results to those presented in other studies [8,33,34,39]. Table 5 shows the results on fine-tune efficiency evaluation.…”

Section: Performance Of the Efficiencymentioning

confidence: 98%

“…Experimental results show that the proposed method has higher classification accuracy than traditional DAGSVM while having an acceptable time cost. The studies in [39] and [47] have conducted research with a focus on lightweight models rather than classification performance. While most studies primarily emphasize performance, they highlight the importance of lightweight approaches for handling large-scale traffic data.…”

Section: Encrypted Traffic Classificationmentioning

confidence: 99%

“…GraphDApp [38], TSCRNN [17], DeepPacket [10], 1D-CNN [26], FastTraffic [39], MATEC [47] (3) Pretraining-based methodologies: PERT [21], ET-BERT (flow) [34], ET-BERT (packet) [34], XENTC [33], BFCN [22], Flow-MAE [25], YaTC [24] Most studies do not perform task #1 (Encapsulation) on the ISCX 2016 VPN/Non-VPN data; rather, they perform tasks #2 (Category) and #3 (Application) to classify categories and applications. Therefore, we compare these methods and approaches that target task #2 and #3, as these tasks are more commonly addressed.…”

Section: Comparison With Other Modelmentioning

confidence: 99%

“…(1) Statistical feature-based methodologies: AppScanner [54], CUMUL [44], BIND [45] (2) ML-and DL-based methodologies: Deep Fingerprinting (DF) [46], FS-Net [15], Graph-DApp [38], TSCRNN [17], DeepPacket [10], 1D-CNN [26], FastTraffic [39], MATEC [47] (3) Pretraining-based methodologies: PERT [21], ET-BERT (flow) [34], ET-BERT (packet) [34],…”

Section: Comparison With Other Modelmentioning

confidence: 99%

“…With the growing concerns regarding personal privacy and security, most applications now utilize encrypted traffic [37][38][39]. As encrypted communications protect payload content, traditional traffic classification methods have become inapplicable.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Fast and Accurate Multi-Task Learning for Encrypted Network Traffic Classification

Park,

Shin,

Baek

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The classification of encrypted traffic plays a crucial role in network management and security. As encrypted network traffic becomes increasingly complicated and challenging to analyze, there is a growing need for more efficient and comprehensive analytical approaches. Our proposed method introduces a novel approach to network traffic classification, utilizing multi-task learning to simultaneously train multiple tasks within a single model. To validate the proposed method, we conducted experiments using the ISCX 2016 VPN/Non-VPN dataset, consisting of three tasks. The proposed method outperformed the majority of existing methods in classification with 99.29%, 97.38%, and 96.89% accuracy in three tasks (i.e., encapsulation, category, and application classification, respectively). The efficiency of the proposed method also demonstrated outstanding performance when compared to methods excluding lightweight models. The proposed approach demonstrates accurate and efficient multi-task classification on encrypted traffic.

show abstract

Section: Performance Of the Efficiencymentioning

confidence: 98%

Section: Encrypted Traffic Classificationmentioning

confidence: 99%