{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T12:50:17Z","timestamp":1776430217121,"version":"3.51.2"},"reference-count":48,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>A difficult NP-hard optimization problem, designing cryptographically robust substitution-boxes (S-boxes) necessitates a careful balancing act between several conflicting properties, such as differential uniformity and nonlinearity. Genetic Algorithms (GAs) have been widely used for this task; however, their performance is often limited by premature convergence and insufficient diversity during crossover operations. This primarily occurs because genetic algorithms commence with limited a priori knowledge. This sort of \u201cblindness\u201d and failure to utilize local knowledge results in diminished performance. In GA, the crossover operations facilitate the dissemination of robust candidates within the population. Conventionally, GA implements crossover for each pair of parents for diversity and a robust solution. However, this is not invariably the situation. To enhance children\u2019s candidacy, parental diversity is quite crucial. This paper proposes a similarity-aware crossover strategy, integrated with a Siamese learning framework, to guide the genetic algorithm for improved S-box optimization with better diversity and faster convergence by utilizing parental local information. The proposed model is similarity-aware to guarantee that the GA improves parental diversity. When the parents exhibit excessive similarity, a \u201cregressive\u201d crossover is opted, which ensures the propagation of a parental couple with sufficient diversity to produce superior offspring. The proposed similarity-aware GA model is applied and evaluated to generate cryptographically robust and optimized S-boxes. To verify the robustness in terms of diversity, the model has been tested using three different loss functions: contrastive loss, KL divergence loss, and the suggested method of combining both loss functions to form a hybrid loss function. The effectiveness of the proposed approach is demonstrated through the generation of high-quality S-boxes with strong cryptographic properties.<\/jats:p>","DOI":"10.3390\/e28040460","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T11:53:46Z","timestamp":1776426826000},"page":"460","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Boosting the Diversity of a Similarity-Aware Genetic Algorithm Using a Siamese Network for Optimized S-Box Generation"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9173-3952","authenticated-orcid":false,"given":"Ishfaq Ahmad","family":"Khaja","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Jamia Millia Islamia, New Delhi 110025, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4915-9325","authenticated-orcid":false,"given":"Musheer","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Jamia Millia Islamia, New Delhi 110025, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8513-0645","authenticated-orcid":false,"given":"Louai A.","family":"Maghrabi","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, College of Engineering, University of Business and Technology, Jeddah, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"268","DOI":"10.33022\/ijcs.v14i1.4596","article-title":"Optimization by nature: A review of genetic algorithm techniques","volume":"14","author":"Waysi","year":"2025","journal-title":"Indones. J. Comput. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1245","DOI":"10.1007\/s12065-023-00822-6","article-title":"Genetic algorithms: Theory, genetic operators, solutions, and applications","volume":"17","author":"Alhijawi","year":"2024","journal-title":"Evol. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1109\/3477.485836","article-title":"Hybrid methods using genetic algorithms for global optimization","volume":"26","author":"Renders","year":"1996","journal-title":"IEEE Trans. Syst. Man Cybern. Part B (Cybern.)"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1007\/s11277-023-10456-7","article-title":"A New S-box Generator Algorithm Based on 3D Chaotic Maps and Whale Optimization Algorithm","volume":"131","author":"Artuger","year":"2023","journal-title":"Wirel. Pers. Commun."},{"key":"ref_5","unstructured":"Daemen, J., and Rijmen, V. (1998, January 20\u201322). AES proposal: Rijndael. Proceedings of the 1st Advance Encryption Conference, Ventura, CA, USA."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Carlet, C. (2005). On highly nonlinear S-boxes and their inability to thwart DPA attacks. International Conference on Cryptology in India, Springer.","DOI":"10.1007\/11596219_5"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Vie, A., Kleinnijenhuis, A.M., and Farmer, D.J. (2020). Qualities, challenges and future of genetic algorithms: A literature review. arXiv.","DOI":"10.2139\/ssrn.3726035"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Alam, T., Qamar, S., Dixit, A., and Benaida, M. (2020). Genetic algorithm: Reviews, implementations, and applications. arXiv.","DOI":"10.36227\/techrxiv.12657173"},{"key":"ref_9","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020). A simple framework for contrastive learning of visual representations. International Conference on Machine Learning, PMLR."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/bs.host.2023.01.003","article-title":"Deep metric learning for computer vision: A brief overview","volume":"48","author":"Mohan","year":"2023","journal-title":"Handb. Stat."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Bello Garc\u00eda, M., Costa, P., N\u00e1poles, G., Mesejo Santiago, P., and Cord\u00f3n Garc\u00eda, \u00d3 (2024). ExplainLFS: Explaining neural architectures for similarity learning from local perturbations in the latent feature space. Inf. Fusion, 108.","DOI":"10.1016\/j.inffus.2024.102407"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sanfins, G., Ramos, F., and Naiff, D. (2025). Similarity learning with neural networks. Phys. Rev. E, 111.","DOI":"10.1103\/PhysRevE.111.025106"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1007\/s10278-013-9591-x","article-title":"A novel similarity learning method via relative comparison for content-based medical image retrieval","volume":"26","author":"Huang","year":"2013","journal-title":"J. Digit. Imaging"},{"key":"ref_14","first-page":"1394","article-title":"DeepSL: Deep Neural Network-based Similarity Learning","volume":"15","author":"Tourad","year":"2024","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_15","unstructured":"Chang, Y., Cai, X., Jensen, C.S., and Qi, J. (2025). K Nearest Neighbor-Guided Trajectory Similarity Learning. arXiv."},{"key":"ref_16","first-page":"33","article-title":"The island model genetic algorithm: On separability, population size and convergence","volume":"7","author":"Whitley","year":"1999","journal-title":"J. Comput. Inf. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1109\/TEVC.2002.800880","article-title":"Parallelism and evolutionary algorithms","volume":"6","author":"Alba","year":"2002","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Skolicki, Z., and De Jong, K. (2005, January 25\u201329). The influence of migration sizes and intervals on island models. Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), Washington, DC, USA.","DOI":"10.1145\/1068009.1068219"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Alba, E., and Dorronsoro, B. (2008). Cellular Genetic Algorithms, Springer.","DOI":"10.1007\/978-0-387-77610-1_1"},{"key":"ref_20","unstructured":"Tomassini, M. (2005). Spatially Structured Evolutionary Algorithms: Artificial Evolution in Space and Time, Springer."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Cant\u00fa-Paz, E. (2000). Efficient and Accurate Parallel Genetic Algorithms, Kluwer Academic Publishers.","DOI":"10.1007\/978-1-4615-4369-5"},{"key":"ref_22","unstructured":"Goldberg, D.E., and Richardson, J. (1987, January 28\u201331). Genetic algorithms with sharing for multimodal function optimization. Proceedings of the Second International Conference on Genetic Algorithms (ICGA), Cambridge, MA, USA."},{"key":"ref_23","unstructured":"Mahfoud, S.W. (1995). Niching Methods for Genetic Algorithms. [Ph.D. Thesis, University of Illinois at Urbana-Champaign]."},{"key":"ref_24","unstructured":"De Jong, K.A. (1975). Analysis of the Behavior of a Class of Genetic Adaptive Systems. [Ph.D. Thesis, University of Michigan]."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/s11831-025-10307-7","article-title":"Unlocking New Potentials in Evolutionary Computation with Complex Network Insights: A Brief Survey","volume":"33","author":"Deng","year":"2026","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Deng, L., and Liu, S. (2025). Collective dynamics of particle swarm optimization: A network science perspective. Phys. A Stat. Mech. Its Appl., 675.","DOI":"10.1016\/j.physa.2025.130778"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1016\/j.physleta.2012.01.009","article-title":"A novel method to design S-box based on chaotic map and genetic algorithm","volume":"376","author":"Wang","year":"2012","journal-title":"Phys. Lett. A"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Msolli, A., Hagui, I., and Helali, A. (2024). Dynamic S-boxes generation for IoT security enhancement: A genetic algorithm approach. Ain Shams Eng. J., 15.","DOI":"10.1016\/j.asej.2024.103049"},{"key":"ref_29","unstructured":"Kuznetsov, O., Poluyanenko, N., Frontoni, E., Arnesano, M., and Smirnov, O. (2024). Evolutionary approach to s-box generation: Optimizing nonlinear substitutions in symmetric ciphers. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.ins.2020.03.025","article-title":"A genetic algorithm for constructing bijective substitution boxes with high nonlinearity","volume":"523","author":"Wang","year":"2020","journal-title":"Inf. Sci."},{"key":"ref_31","first-page":"211","article-title":"An Improved S-box Generation Method using Metaheuristic Optimization Technique","volume":"10","author":"Vashishta","year":"2021","journal-title":"Int. J. Eng. Res. Technol."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Garipcan, A.M., Ayd\u0131n, Y., and \u00d6zkaynak, F. (2025). A novel s-box generation method based on metastable inducing over FPGA for block ciphers. Knowl.-Based Syst., 310.","DOI":"10.1016\/j.knosys.2025.112968"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"116132","DOI":"10.1109\/ACCESS.2020.3004449","article-title":"Particle swarm optimization based highly nonlinear substitution-boxes generation for security applications","volume":"8","author":"Ahmad","year":"2020","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1109\/CVPR.2006.100","article-title":"Dimensionality reduction by learning an invariant mapping","volume":"Volume 2","author":"Hadsell","year":"2006","journal-title":"2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201906)"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"ref_36","unstructured":"Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv."},{"key":"ref_37","unstructured":"Smith, L.N. (2018). A disciplined approach to neural network hyper-parameters: Part 1\u2014Learning rate, batch size, momentum, and weight decay. arXiv."},{"key":"ref_38","unstructured":"Pascanu, R., Mikolov, T., and Bengio, Y. (2013). On the difficulty of training recurrent neural networks. International Conference on Machine Learning, PMLR."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Carlet, C., Crama, Y., and Hammer, P.L. (2010). Boolean Functions for Cryptography and Error-Correcting Codes. Boolean Models and Methods in Mathematics, Computer Science, and Engineering, Cambridge University Press.","DOI":"10.1017\/CBO9780511780448.011"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/0097-3165(76)90024-8","article-title":"On \u201cbent\u201d functions","volume":"20","author":"Rothaus","year":"1976","journal-title":"J. Comb. Theory Ser. A"},{"key":"ref_41","unstructured":"Nyberg, K. (1993). Differentially uniform mappings for cryptography. Workshop on the Theory and Application of Cryptographic Techniques, Springer."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1080\/1023697X.2012.10669006","article-title":"An Improved Method to Obtaining S-Box Based on Chaos and Genetic Algorithm","volume":"19","author":"Yong","year":"2012","journal-title":"HKIE Trans."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3349","DOI":"10.1109\/TCYB.2018.2846186","article-title":"Design of highly non-linear substitution boxes based on I-Ching operators","volume":"48","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Cybern."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Ejaz, A., Murtaza, G., Haider, T., Azam, N.A., and Hayat, U. (2025). An Efficient S-Box Generation with Mutation Optimization for Secure Image Encryption. Secur. Priv., 8.","DOI":"10.1002\/spy2.70068"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Zhang, R., Shu, R., Wei, Y., Zhang, H., and Wu, X. (2023). A Novel S-Box Generation Methodology Based on the Optimized GAN Model. Comput. Mater. Contin., 76.","DOI":"10.32604\/cmc.2023.041187"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Tong, X., Cheng, L., Wang, Z., and Zhang, M. (2024). Design of S-box multi-objective optimization algorithm based on combined chaotic system. Phys. Scr., 99.","DOI":"10.1088\/1402-4896\/ad1282"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"4051","DOI":"10.1007\/s00521-022-07899-7","article-title":"Utilizing the roulette wheel based social network search algorithm for substitution box construction and optimization","volume":"35","author":"Zamli","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Shadab, M., Jawed, M.S., and Sajid, M. (2025). Substitution Box Construction Using Transfer-Function Assisted Metaheuristic and Booster Algorithm: A Hybrid Approach. Secur. Priv., 8.","DOI":"10.1002\/spy2.462"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/4\/460\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T11:58:03Z","timestamp":1776427083000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/4\/460"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,17]]},"references-count":48,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["e28040460"],"URL":"https:\/\/doi.org\/10.3390\/e28040460","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,17]]}}}