Search

The increased complexity of hardware and software resources and the asynchronous interaction among components (such as servers, end devices, network, services and software) make fault detection and recovery very challenging. In this paper, we present innovative concepts for fault detection, root cause analysis and self-healing architectures analyzing the duration of pattern transition sequences during an execution window. In this approach, all interactions among components of Pervasive Computing Systems (PCS) are monitored and analyzed. We use three-dimensional array of features to capture spatial and temporal variability to be used by an anomaly analysis engine to immediately generate an alert when abnormal behavior pattern is captured indicating some kind of software or hardware failure. The main contributions of this paper include the innovative analysis methodology and feature selection to detect and identify anomalous behavior. Evaluating the effectiveness of this approach to detect faults injected asynchronously shows a detection rate of above 99.9% with no occurrences of false alarms for a wide range of scenarios.

Though mobile computing systems constitute the core of the next generation ubiquitous pervasive services, they still have many flaws in their security. This paper describes a novel framework for wireless anomaly based intrusion detection and response system, which is capable of detecting complex malicious attacks. This framework is based on multi-channel online monitoring and analysis of wireless network features with respect to multiple observation time windows. These features are related to Data Link Layer frame behaviors and the mobility of stations. A general purpose wireless self-protection system (WSPS) is presented. WSPS has the following modules: Wireless network probes, Wireless features filtration and generation module, Wireless network flow generator, behavior analysis module, and action module. WSPS self protects against attacks by online monitoring and analyzing anomalies and misuses in the network features, and utilizes the low false alerts of the analysis module. The validation and effectiveness of this framework is carried out by experimenting with more than 20 different types of wireless attacks using Wireless LANs (WLANs). Our experimental results show that our approach can protect from wireless network attacks with average false-positive rate of 2.234%, and average detection rate of 99.13% for all the experimented attacks.