Multimedia Traffic Anomaly Detection

TL;DR

This paper introduces Meta-UAD, a meta-learning approach for detecting anomalies in user-level social multimedia traffic, effectively handling new classes with few samples and reducing computational costs.

Contribution

The paper proposes Meta-UAD, a meta-learning scheme with a specialized feature extractor, to improve anomaly detection in social multimedia traffic with limited labeled data.

Findings

Meta-UAD outperforms existing models on public datasets.

The feature extractor enhances detection accuracy.

Meta-UAD adapts quickly to new anomaly classes.

Abstract

Accuracy anomaly detection in user-level social multimedia traffic is crucial for privacy security. Compared with existing models that passively detect specific anomaly classes with large labeled training samples, user-level social multimedia traffic contains sizeable new anomaly classes with few labeled samples and has an imbalance, self-similar, and data-hungry nature. Recent advances, such as Generative Adversarial Networks (GAN), solve it by learning a sample generator only from seen class samples to synthesize new samples. However, if we detect many new classes, the number of synthesizing samples would be unfeasibly estimated, and this operation will drastically increase computational complexity and energy consumption. Motivation on these limitations, in this paper, we propose \textit{Meta-UAD}, a Meta-learning scheme for User-level social multimedia traffic Anomaly Detection. This scheme relies on the episodic training paradigm and learns from the collection of K-way-M-shot classification tasks, which can use the pre-trained model to adapt any new class with few samples by going through few iteration steps. Since user-level social multimedia traffic emerges from a complex interaction process of users and social applications, we further develop a feature extractor to improve scheme performance. It extracts statistical features using cumulative importance ranking and time-series features using an LSTM-based AutoEncoder. We evaluate our scheme on two public datasets and the results further demonstrate the superiority of Meta-UAD.