Payload-based anomaly detection in HTTP traffic

Publication Type:
Thesis
Issue Date:
2012
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail01Front.pdf258.17 kB
Adobe PDF
Thumbnail02Whole.pdf3.05 MB
Adobe PDF
Internet provides quality and convenience to human life but at the same time it provides a platform for network hackers and criminals. Intrusion Detection Systems (IDSs) have been proven to be powerful methods for detecting anomalies in the network. Traditional IDSs based on signatures are unable to detect new (zero days) attacks. Anomaly-based systems are alternative to signature based systems. However, present anomaly detection systems suffer from three major setbacks: (a) Large number of false alarms, (b) Very high volume of network traffic due to high data rates (Gbps), and (c) Inefficiency in operation. In this thesis, we address above issues and develop efficient intrusion detection frameworks and models which can be used in detecting a wide variety of attacks including web-based attacks. Our proposed methods are designed to have very few false alarms. We also address Intrusion Detection as a Pattern Recognition problem and discuss all aspects that are important in realizing an anomaly-based IDS. We present three payload-based anomaly detectors, including Geometrical Structure Anomaly Detection (GSAD), Two-Tier Intrusion Detection system using Linear Discriminant Analysis (LDA), and Real-time Payload-based Intrusion Detection System (RePIDS), for intrusion detection. These detectors perform deep-packet analysis and examine payload content using n-gram text categorization and Mahalanobis Distance Map (MDM) techniques. An MDM extracts hidden correlations between the features within each payload and among packet payloads. GSAD generates model of normal network payload as geometrical structure using MDMs in a fully automatic and unsupervised manner. We have implemented the GSAD model in HTTP environment for web-based applications. For efficient operation of IDSs, the detection speed is a key point. Current IDSs examine a large number of data features to detect intrusions and misuse patterns. Hence, for quickly and accurately identifying anomalies of Internet traffic, feature reduction becomes mandatory. We have proposed two models to address this issue, namely two-tier intrusion detection model and RePIDS. Two-tier intrusion detection model uses Linear Discriminant Analysis approach for feature reduction and optimal feature selection. It uses MDM technique to create a model of normal network payload using an extracted feature set. RePIDS uses a 3-tier Iterative Feature Selection Engine (IFSEng) to reduce dimensionality of the raw dataset using Principal Component Analysis (PCA) technique. IFSEng extracts the most significant features from the original feature set and uses mathematical and graphical methods for optimal feature subset selection. Like two-tier intrusion detection model, RePIDS then uses MDM technique to generate a model of normal network payload using extracted features. We test the proposed IDSs on two publicly available datasets of attacks and normal traffic. Experimental results confirm the effectiveness and validation of our proposed solutions in terms of detection rate, false alarm rate and computational complexity.
Please use this identifier to cite or link to this item: