No abstract

SummaryVoice and video over IP are becoming increasingly popular and represent the largest source of profits as consumer interest in online voice and video services increases, and as broadband deployments proliferate. In order to tap the potential profits that VoIP and IPTV offer, carrier networks have to efficiently and accurately manage and track the delivery of IP services. The traditional approach of using port numbers to classify traffic is infeasible due to the usage of dynamic port number. In this paper, we focus on a statistical pattern classification technique to identify multimedia traffic. Based on the intuitions that voice and video data streams show strong regularities in the packet inter-arrival times and the associated packet sizes when combined together in one single stochastic process, we propose a system, called VOVClassifier , for voice and video traffic classification. VOVClassifier is an automated self-learning system that classifies traffic data by extracting features from frequency domain using Power Spectral Density analysis and grouping features using Subspace Decomposition. We applied VOVClassifier to real packet traces collected from different network scenarios. Results demonstrate the effectiveness and robustness of our approach that is capable of achieving a detection rate of up to 100% for voice and 96.5% for video while keeping the false positive rate close to 0%.

No abstract

Abstract-Despite the rapid advance in networking technologies, detection of network anomalies at high-speed switches/routers is still far from maturity. To push the frontier, two major technologies need to be addressed. The first one is efficient feature-extraction algorithms/hardware that can match a line rate in the order of Gb/s; the second one is fast and effective anomaly detection schemes. In this paper, we focus on design of efficient data structure and algorithms for feature extraction. Specifically, we propose a novel data structure that extracts socalled two-directional (2D) matching features, which are shown to be effective indicators of network anomalies. Our key idea is to use a Bloom filter array to trade off a small amount of accuracy in feature extraction, for much less space and time complexity, so that our data structure can catch up with a line rate in the order of Gb/s. Different from the existing work, our data structure has the following properties: 1) dynamic Bloom filter, 2) combination of a sliding window with Bloom filter, and 3) using an insertion-removal pair to enhance Bloom filter with a removal operation. Our analysis and simulation demonstrate that the proposed data structure has a better space/time tradeoff than conventional algorithms. For example, for a fixed time complexity, the conventional algorithm (i.e., hash table [1]-[8]) requires a memory of 1.01G bits while our data structure requires a memory of only 62.9M bits, at the cost of losing 1% accuracy in feature extraction.

In this paper, we study the problem of feature extraction for pattern classification applications. RELIEF is considered as one of the best-performed algorithms for assessing the quality of features for pattern classification. Its extension, local feature extraction (LFE), was proposed recently and was shown to outperform RELIEF. In this paper, we extend LFE to the nonlinear case, and develop a new algorithm called kernel LFE (KLFE). Compared with other feature extraction algorithms, KLFE enjoys nice properties such as low computational complexity, and high probability of identifying relevant features; this is because KLFE is a nonlinear wrapper feature extraction method and consists of solving a simple convex optimization problem. The experimental results have shown the superiority of KLFE over the existing algorithms.