Quantization-aware Neural Architectural Search for Intrusion Detection

arXiv:2311.04194v2 Announce Type: replace
Abstract: Deploying machine learning-based intrusion detection systems (IDSs) on hardware devices is challenging due to their limited computational resources, power consumption, and network connectivity. Hence, there is a significant need for robust, deep learning models specifically designed with such constraints in mind. In this paper, we present a design methodology that automatically trains and evolves quantized neural network (NN) models that are a thousand times smaller than state-of-the-art NNs but can efficiently analyze network data for …

arxiv aware computational connectivity constraints cs.cr deep learning design detection devices hardware idss intrusion intrusion detection machine machine learning network network connectivity power resources search systems