Abstract
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.
Highlights
The Internet has become an indispensable part of our lives at work and in our home applications, such as personal health assistants, remote health monitoring, and smart home security
We describe a privacy-preserving distributed intrusion detection system (IDS) model based on incremental learning, that identifies a Denial of Service (DoS) attacks
We focused on feature extraction and later on detection accuracies of the Convolutional Neural Network (CNN) classifier for different datasets
Summary
The Internet has become an indispensable part of our lives at work and in our home applications, such as personal health assistants, remote health monitoring, and smart home security. The remote monitoring applications especially health applications generate a large volume of continuous data from vital signs and other signals (e.g., EEG, ECG). This health data is confidential so we want to ensure that the data privacy is not violated. Any tampering of the data by an attacker can cause a serious issue, such as false diagnosis, delay in an emergency, and other health complications, which can lead to death [1] In this new era, a shift to digital transactions in different applications mandates a shift in our mindset to secure all these transactions as they traverse small IoT sensors or home appliances. Despite various security practices such as authentication, encryption, and access controls, security practitioners recommend active network monitoring and adaptable Intrusion Detection
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
