[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290556-105":59,"doc-detail-290556-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","classifying-world-war-ii-era-ciphers-with-machine-learning-abstract","Classifying World War II Era Ciphers with Machine Learning - Abstract","","Determine the accuracy of machine learning and deep learning methods for classifying selected World War II era cipher machines using only ciphertext. The study targets Enigma, M-209, Sigaba, Purple, and Typex, testing classic models (SVM, k-Nearest Neighbors, Random Forest) and deep neural networks (MLP, LSTM, ELM, CNN). Features include histograms, digrams, and raw ciphertext letter sequences, evaluated under four plaintext/key scenarios. With 1000 characters per ciphertext in the most realistic setting, classification exceeds 97% accuracy, and classic methods perform at least as well as deep models.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/classifying-world-war-ii-era-ciphers-with-machine-learning-abstract/290556/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/classifying-world-war-ii-era-ciphers-with-machine-learning-abstract/290556.png","ImageObject",300,407,{"name":92,"@type":93},"Liam","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-23","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Which cipher machines are classified in this study?","Question",{"text":113,"@type":114},"The experiments classify five World War II era ciphers: Enigma, M-209, Sigaba, Purple, and Typex.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What learning models are evaluated?",{"text":118,"@type":114},"The paper evaluates three classic machine learning models (SVM, k-NN, Random Forest) and four deep learning models (MLP, LSTM, ELM, CNN).",{"name":120,"@type":111,"acceptedAnswer":121},"How is classification accuracy measured and what is the best reported result?",{"text":122,"@type":114},"Models are trained on features derived from ciphertext (histograms, digrams, and raw letter sequences) and tested under scenarios with fixed/random plaintext and fixed/random keys. With 1000 ciphertext characters in the most realistic scenario, the study reports greater than 97% accuracy.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},290556,1789642073,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},8796095461564,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","arXiv :2307 .00501v2 [ cs .LG] 30 Aug 2023  \nClassifying World War II Era Ciphers with Machine  \nLearning Brooke Dalton∗ Mark Stamp∗†  \nAugust 31, 2023  \nAbstract  \nWe determine the accuracy with which machine learning and deep learning techniques can classify selected World War II era ciphers when only ciphertext is available. The specific ciphers considered are Enigma, M-209 , Sigaba, Purple, and Typex. We experiment with three classic machine learning models, namely, Support Vector Machines (SVM), 􀁫-Nearest Neighbors (􀁫-NN), and Random Forest (RF) . We also experiment with four deep learning neural network-based models: Multi-Layer Perceptrons (MLP), Long Short-Term Memory (LSTM), Extreme Learning Machines (ELM), and Convolutional Neural Networks (CNN) . Each model is trained on features consisting of histograms, digrams, and raw ciphertext letter sequences. Furthermore, the classification problem is considered under four distinct scenarios: Fixed plaintext with fixed keys, random plaintext with fixed keys, fixed plaintext with random keys, and random plaintext with random keys. Under the most realistic scenario, given 1000 characters per ciphertext, we are able to distinguish the ciphers with greater than 97% accuracy. In addition, we consider the accuracy of a subset of the learning techniques asa function of the length of the ciphertext messages. Somewhat surprisingly, our classic machine learning models perform at least as well as our deep learning models. We also find that ciphers that are more similar in design are somewhat more challenging to distinguish, but not as difficult as might be expected.  \n1 Introduction  \nMany cipher machines were created and utilized by various nations during World War II. For example, the Enigma is a rotor-based cipher machine that was invented as a commercial product and was later modified and deployed by the German military. Other rotor-based cipher machines of the same era include the M-209 Converter (henceforth, simply referred to as M-209) and Sigaba, which  \n∗ Department of Computer Science, San Jose State University †[mark.stamp@sjsu.edu](mark.stamp@sjsu.edu)  \nwere both created by the United States, and the British-built Typex. The wellknown Purple cipher machine that was used by Japan in World War II employed a switch-based system. Although these ciphers have all been broken [4, 5 , 10 , 25], and cryptography has improved significantly since World War II, accurately classifying ciphertext generated by these machines is an interesting challenge. There has been previous research on classifying classic ciphers by applying machine learning techniques [14, 15 , 16 , 17 , 20], but as far as the authors are aware, to date no such work has focused on the WWII-era cipher machines considered in this paper.  \nOur research examines whether machine learning and deep learning techniques can classify selected World War II era ciphers when only ciphertext is provided. We consider the five ciphers mentioned above, namely, Enigma, M-209 , Purple, Sigaba, and Typex. For each cipher, we train and test machine learning techniques based on a variety of features; specifically, the raw ciphertext letter sequence, letter histograms, and letter digram statistics. We experiment with three popular classic machine learning techniques, namely, Support Vector Machines (SVM), 􀁫-Nearest Neighbors (􀁫-NN), and Random Forest (RF) models. Additionally, we experiment with four deep learning techniques, namely, MultiLayer Perceptrons (MLP), Long Short-Term Memory (LSTM) models, Extreme Learning Machines (ELM), and Convolutional Neural Networks (CNN) . We train and test models under four distinct scenarios, and we find that in the most realistic case, given sufficient ciphertext, we can identify the correct cipher machine with accuracy in excess of 97% . We also conduct experiments to determine the relationship between the ciphertext length and the accuracy of our various models.  \nThe remainder of this paper is organ","cbCaiuAF2B5J1f9V","https://ap.wps.com/l/cbCaiuAF2B5J1f9V","pdf",7389240,48,"English","# Abstract\n# 1 Introduction\n## 1 Introduction\n# 2 Background\n## 2.1 World War II Ciphers\n### 2.1.1 Enigma","[{\"question\":\"Which cipher machines are classified in this study?\",\"answer\":\"The experiments classify five World War II era ciphers: Enigma, M-209, Sigaba, Purple, and Typex.\"},{\"question\":\"What learning models are evaluated?\",\"answer\":\"The paper evaluates three classic machine learning models (SVM, k-NN, Random Forest) and four deep learning models (MLP, LSTM, ELM, CNN).\"},{\"question\":\"How is classification accuracy measured and what is the best reported result?\",\"answer\":\"Models are trained on features derived from ciphertext (histograms, digrams, and raw letter sequences) and tested under scenarios with fixed/random plaintext and fixed/random keys. With 1000 ciphertext characters in the most realistic scenario, the study reports greater than 97% accuracy.\"}]","Classifying World War II Era Ciphers with Machine Learning - Abstract | PDF",121]