Analyzing the impact of shifts in encrypted mobile-app traffic on multimodal few-shot learning
Анализ влияния изменений в зашифрованном трафике мобильных приложений на мультимодальное обучение по малому числу примеров
2025-12-15
SCID: 54.1/vqdxq2t2
Discuss with AI
Meta Mimeticencrypted mobile-app trafficmultimodal few-shot learningtraffic classificationtraffic shifts
Figures from the paper
Abstract (AI)
Network management is essential for ensuring efficient and secure Internet operations, with traffic classification serving as a core element. Currently, traffic classification is facing increasing challenges due to the growing presence of highly dynamic mobile-app traffic , being fueled by the continuous release of new apps, frequent updates, evolving communication patterns, and stricter encrypted protocols. These shifts can significantly alter traffic patterns, making it difficult to keep state-of-the-art machine and deep learning-based traffic classifiers up to date, due to the severe lack of current, high-quality traffic datasets needed to train and adapt such data-driven models. Few-Shot Learning ( FSL ) offers a promising solution by enabling classification even when only a limited amount of labeled traffic data is available. However, the investigation of FSL in the domain of traffic classification is still in its early stages, with the impact of traffic shifts being largely underexplored. In this paper, we evaluate how the traffic from new apps (those unseen during training) and shifted apps (those affected by traffic changes) impacts classification performance by leveraging Meta Mimetic , a state-of-the-art multimodal FSL approach. Meta Mimetic exploits multiple views of traffic data and integrates an ad-hoc learning procedure to adapt to the evolving mobile-app traffic using minimal supervised data. Our experiments are conducted on two publicly available datasets, encompassing both new apps and shifted apps. First, we assess the presence of traffic changes in shifted apps through Markov-based statistical modeling and evaluate the impact on the performance of Meta Mimetic when considering such traffic. We then show that Meta Mimetic exhibits strong adaptability to shifts introduced by stricter encrypted protocols, having a performance degradation 2 × lower than single-modal baselines, as further validated using eXplainable AI (XAI) . Finally, in case of extreme data scarcity, we show that Meta Mimetic can effectively use old traffic for data augmentation, regardless of shifts, achieving up to a + 12 % F1-score improvement over alternative methods.
Key Findings
1
Explainable AI analyses further validate Meta Mimetic’s robustness to encrypted mobile-app traffic shifts.
2
Markov-based statistical modeling is used to identify and characterize traffic changes in shifted applications.
3
Meta Mimetic adapts strongly to stricter encrypted-protocol shifts, showing twofold lower performance degradation than single-modal baselines.
4
Meta Mimetic combines multiple traffic views with an adaptive learning procedure to classify evolving app traffic using minimal labeled data.
5
The study evaluates how unseen new apps and traffic-shifted apps affect few-shot encrypted mobile-app traffic classification.
Research Object
encrypted mobile-app traffic, including traffic from new and traffic-shifted apps
Research Subject
the impact of traffic shifts on multimodal few-shot traffic-classification performance and adaptability
Publication Details
Publication Date
2025-12-15
Journal
Publisher
ISSN
Cited by
3
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest