A joint research team comprising Professor Kim Ji Hye and Dr. Lee Seung Hwa from our university's Department of Electrical Engineering, along with Professor Hyun-Ok Oh and Dr. Han-Kyung Ko from Hanyang University's Department of Information Systems, has been awarded the 2024 Best Paper Award by the IEEE Transactions on Dependable and Secure Computing (TDSC) journal for their paper titled “vCNN: Verifiable Convolutional Neural Network Based on zk-SNARKs.”

This paper proposes a technique to cryptographically verify the computational results of **convolutional neural networks (CNNs)**, primarily used for image recognition. While existing AI models operated like a ‘black box,’ making it difficult to verify the reliability of their results, the joint research team solved this problem by utilizing zk-SNARKs, a zero-knowledge proof technology.

Notably, this research achieved a breakthrough by significantly reducing the high computational complexity inherent in zk-SNARKs-based verification methods. This was a field where many research teams attempted to tackle the extremely high technical difficulty but faced challenges in practical implementation. By successfully solving this difficult problem, the joint research team expects to significantly contribute to expanding the scope of AI application in fields where accuracy and reliability are essential, such as medical diagnosis and autonomous driving.

Meanwhile, IEEE TDSC is a top-tier journal in the fields of computer system reliability, security, and privacy, ranking within the top 5% of journals in software engineering. Given that only one paper is selected as the best paper annually from hundreds of submissions, this award signifies that the joint research team's achievements have gained international recognition for their innovation and significance in the fields of AI and security.