TY - GEN
T1 - Lightweight AI-Enhanced Intrusion Detection System for Zero-Day Threat Detection in Consumer Electronics Devices
AU - Gaurav, Akshat
AU - Arya, Varsha
AU - Wu, Jinsong
AU - Chui, Kowk Tai
AU - Gupta, Brij B.
N1 - Publisher Copyright:
© 2026 IEEE.
PY - 2026
Y1 - 2026
N2 - 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.
AB - 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.
KW - Consumer Electronics Security
KW - Lightweight Intrusion Detection System
KW - Mahalanobis Distance
KW - Zero-Day Attack Detection
UR - https://www.scopus.com/pages/publications/105037338428
U2 - 10.1109/ICCE67443.2026.11449631
DO - 10.1109/ICCE67443.2026.11449631
M3 - Conference contribution
AN - SCOPUS:105037338428
T3 - Digest of Technical Papers - IEEE International Conference on Consumer Electronics
BT - 2026 IEEE International Conference on Consumer Electronics, ICCE 2026
T2 - 2026 IEEE International Conference on Consumer Electronics, ICCE 2026
Y2 - 3 February 2026 through 5 February 2026
ER -