New method uses And-Inverter Graphs for scalable hardware Trojan detection

Researchers have developed a novel method for detecting hardware Trojans in large-scale System-on-Chip (SoC) designs by representing them as And-Inverter Graphs (AIGs). This approach utilizes knowledge graph embeddings to create compact, constant-size representations of circuit structures, allowing for linear scaling of complexity with the number of edges. The method enables symbolic learning across deep datapaths to identify rare, inconsistent connections indicative of Trojans, demonstrating practical scalability and clear separation between Trojan and benign nodes in experiments. AI

RANK_REASON The cluster contains a research paper detailing a new method for hardware security. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• And-Inverter Graphs
• arXiv
• Hardware Trojan
• knowledge graph embedding
• system on a chip
• Yaroslav Popryho

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →