Lightweight AI-Enhanced Intrusion Detection System for Zero-Day Threat Detection in Consumer Electronics Devices

View at publisher Summarise with VIRAT
Authors: Akshat Gaurav, Varsha Arya, Jinsong Wu, Kwok Tai Chui, Brij B. Gupta
Cited by: 0
References: 17

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The increasing connectivity of consumer electronic devices has made them highly susceptible to emerging and unknown cyber threats, including zero-day attacks that traditional intrusion detection systems often fail to identify. To address this challenge, a lightweight artificial intelligence–driven framework is introduced for efficient and adaptive intrusion detection. The model leverages the CIC-DDoS2019 dataset, using SYN and benign traffic for training and UDP traffic to simulate zero-day conditions. It integrates categorical embeddings, normalized continuous features, and compact neural layers with attention refinement to enhance feature discrimination. With only 21,243 trainable parameters, the framework achieves high detection accuracy (AUROC = 0.9968) and robust zero-day recognition (AUROC = 0.8769), offering a scalable, energy-efficient solution for securing next-generation consumer devices.

Fields of Study & Subjects

Network Security and Intrusion Detection Network Packet Processing and Optimization Internet Traffic Analysis and Secure E-voting

Publication details

Journal / source
International Conference on Consumer Electronics
Pages
1–6
Publication date
3 February 2026
Language
EN