Existing techniques for incremental learning are computationally expensive and produce duplicate features leading to higher false positive and true negative rates. We propose a novel privacy-preserving intrusion detection pipeline for distributed incremental learning. Our pre-processing technique eliminates redundancies and selects unique features by following innovative extraction techniques. We use autoencoders with non-negativity constraints, which help us extract less redundant features. More importantly, the distributed intrusion detection model reduces the burden on the edge classifier and distributes the load among IoT and edge devices. Theoretical analysis and numerical experiments have shown lower space and time costs than state of the art techniques, with comparable classification accuracy. Extensive experiments with standard data sets and real-time streaming IoT traffic give encouraging results.
INDEX TERMSDeep learning, internet of things (IoT), intrusion detection system (IDS), incremental learning, pre-processing.
Internet of Things (IoT) is the interconnection of heterogeneous smart devices through the Internet with diverse application areas. The huge number of smart devices and the complexity of networks has made it impossible to secure the data and communication between devices. Various conventional security controls are insufficient to prevent numerous attacks against these information-rich devices. Along with enhancing existing approaches, a peripheral defence, Intrusion Detection System (IDS), proved efficient in most scenarios. However, conventional IDS approaches are unsuitable to mitigate continuously emerging zero-day attacks. Intelligent mechanisms that can detect unfamiliar intrusions seems a prospective solution. This article explores popular attacks against IoT architecture and its relevant defence mechanisms to identify an appropriate protective measure for different networking practices and attack categories. Besides, a security framework for IoT architecture is provided with a list of security enhancement techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.