The Session Initiation Protocol (SIP) is the de facto standard for user's session control in the next generation Voice over Internet Protocol (VoIP) networks based on the IP Multimedia Subsystem (IMS) framework. In this paper, we first analyze the role of SIP based floods in the Denial of Service (DoS) attacks on the IMS. Afterwards, we present an online intrusion detection framework for detection of such attacks. We analyze the role of different evolutionary and non-evolutionary classifiers on the classification accuracy of the proposed framework. We have evaluated the performance of our intrusion detection framework on a traffic in which SIP floods of varying intensities are injected. The results of our study show that the evolutionary classifiers like sUpervised Classifier System (UCS) and Genetic clASSIfier sySTem (GAssist) can even detect low intensity SIP floods in realtime. Finally, we formulate a set of specific guidelines that can help VoIP service providers in customizing our intrusion detection framework by selecting an appropriate classifier-depending on their requirements in different service scenarios.

The multimedia communication is rapidly converging towards Voice over Internet - commonly known as Voice over Internet Protocol (VoIP). Session Initiation Protocol (SIP) is the standard used for session signaling in VoIP. Crafty attackers can launch a number of Denial of Service (DoS) attacks on a SIP based VoIP infrastructure that can severely compromise its reliability. In contrast, little work is done to analyze the robustness and reliability of SIP severs under DoS attacks. In this paper, we show that the robustness and reliability of generic SIP servers is inadequate than commonly perceived. We have done our study using a customized analysis tool that has the ability to synthesize and launch different types of attacks. We have integrated the tool in a real SIP test bed environment to measure the performance of SIP servers. Our measurements show that a standard SIP server can be easily overloaded by sending simple call requests. We define the performance metrics to measure the effects of flooding attacks on real time services - VoIP in SIP environment - and show the results on different SIP server implementations. Our results also provide insight into resources' usage by SIP servers under flooding attacks. Moreover, we show that how a well known open source SIP server can be crashed through 'INVITE of Death' - a malformed SIP packet maliciously crafted by our tool.

The IP multimedia subsystem (IMS) framework uses session initiation protocol (SIP) for signaling and control of sessions. In this paper, we first demonstrate that SIP flooding attacks on IMS can result in denial of service to the legitimate users. Afterwards, we report our comparative study of three well-known anomaly detection algorithms, adaptive threshold, cumulative sum, and Hellinger distance for detection of flood attacks in IMS. We evaluate the accuracy of the algorithms using a comprehensive traffic dataset that consists of varying benign and malicious traffic patterns.

Due to the recent security infringement incidents of single factor authentication services, there is an inclination towards the use of multi-factor authentication (MFA) mechanisms. These MFA mechanisms should be available to use on modern hand-held computing devices like smart phones due to their big share in computational devices market. Moreover, the high social acceptability and ubiquitous nature has attracted the enterprises to offer their services on modern day hand-held devices. In this regard, the big challenge for these enterprises is to ensure security and privacy of users. To address this issue, we have implemented a verification system that combines human inherence factor (handwritten signature biometrics) with the standard knowledge factor (user specific passwords) to achieve a high level of security. The major computational load of the aforementioned task is shifted on a cloud based application server so that a platform-independent user verification service with ubiquitous access becomes possible. Custom applications are built for both the iOS and Android based devices which are linked with the cloud based two factor authentication (TFA) server. The system is tested on-the-run by a diverse group of users and 98.4% signature verification accuracy is achieved.