2019/11/11 by Ya Xiao, Xiao, Ya, Qingying Hao +3 · 2 citations
Computer Science · #Algorithm #Artificial intelligence #Artificial neural network #Block cipher #Chaos-based Image/Signal Encryption #Cipher #Computer engineering #Computer science #Computer security #Cryptanalysis #Cryptographic Implementations and Security #Cryptography #Cryptography and Security (cs.CR) #Differential cryptanalysis #Encryption #FOS: Computer and information sciences #Physical Unclonable Functions (PUFs) and Hardware Security #Stream cipher #Theoretical computer science #cs.CR
paper · pdf · doi:10.48550/arxiv.1911.04020
published in arXiv (Cornell University) (Cornell University) · 8 pages, 8 figures, The 2019 IEEE Conference on Dependable and Secure Computing
openalex publication_date 2019/11/11 · openalex created_date 2019/11/22 · arxiv created 2019/11/26 · arxiv updated 2019/11/27 · openalex updated_date 2026/08/06
Many real-world cyber-physical systems (CPS) use proprietary cipher algorithms. In this work, we describe an easy-to-use black-box security evaluation approach to measure the strength of proprietary ciphers without having to know the algorithms. We quantify the strength of a cipher by measuring how difficult it is for a neural network to mimic the cipher algorithm. We define new metrics (e.g., cipher match rate, training data complexity and training time complexity) that are computed from neural networks to quantitatively represent the cipher strength. This measurement approach allows us to directly compare the security of ciphers. Our experimental demonstration utilizes fully connected neural networks with multiple parallel binary classifiers at the output layer. The results show that when compared with round-reduced DES, the security strength of Hitag2 (a popular stream cipher used in the keyless entry of modern cars) is weaker than 3-round DES.