MUMBAI, India, June 30 -- Intellectual Property India has published a patent application (202641075079 A) filed by Vardhaman College Of Engineering on June 17, 2026, for Deep Learning Approach For Hardware Trojan Detection In Vlsi Architectures.
Inventors include Sangeeta Singh; I. Babu; Tareeq Zaid; M. Geethanjali; D. Gurunath; R. Mohanjali; Kalimuthu Keerthika; Mohammed Apsa Tabassum; and Allampally Srishanth.
The application for the patent was published on June 26, 2026, under issue no. 26/2026.
Abstract: Deep Learning Approach for Hardware Trojan Detection in VLSI Architectures is the proposed invention. The present invention aims at Deep learning approach for effective and accurate detection of hardware Trojans. The proposed approach employs state-of-the-art neural network models to analyse structural and behavioural characteristics of integrated circuits such as power consumption behaviours, timing variations, switching activities, and netlist representation. Architectures such as Convolutional Neural Networks, Recurrent Neural Networks and Graph Neural Networks are used to effectively capture the geographical, temporal and topological data associated with Trojan activity. The presented methodology provides a scalable, adaptive and high-performance solution for the protection of VLSI systems against hardware Trojans. This reduces dependence on exhaustive testing methods and improves the confidence in detection, and is thus well suited for use in modern semiconductor design and verification flows.
Disclaimer: Curated by HT Syndication.
