Convolutional neural network designed as small truth tables, application to cryptography, formal verification & explainability

• Main Author: Benamira, Adrien
• Other Authors: Thomas Peyrin
• Format: Thesis-Doctor of Philosophy
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science; Mathematical Sciences; Deep convolutional neural network; Machine/deep learning; Cryptanalysis; Neural distinguisher; Exact global xplainability; Side-channel attacks; Fully homomorphic encryption
• Online Access: https://hdl.handle.net/10356/177203
• Institution: Nanyang Technological University

DCNNs have revolutionized machine learning (ML) and deep learning (DL), achieving remarkable success in image recognition, natural language processing, and other domains. However, their deployment in security-critical industries such as cybersecurity, energy, finance, and the military faces persiste...