[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81616-en":3,"doc-seo-81616-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},81616,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generation","Supervised detection of network attacks remains essential for network intrusion detection systems (NIDS) as adversaries adopt advanced strategies enabled by generative AI and reinforcement learning. The work tackles two tasks using a unified multimodal dataset built from reprocessed CIC-IDS-2017, CIC-IoT-2023, UNSW-NB15 and CIC-DDoS-2019 in a shared feature space. The first task trains stable ML classifiers with stratified cross validation; the second generates synthetic data via adversarial learning, comparing fidelity, utility and privacy using SDV framework metrics, f-divergences, distinguishability and non-parametric statistical tests.","Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic  \nData Generation  \nIakovos-Christos Zarkadis  \nUniversity of Piraeus Athens, Greece [iakovos.zarkadis@gmail.com](iakovos.zarkadis@gmail.com)  \nChristos Douligeris  \nDept. of Informatics University of Piraeus Piraeus, Greece [cdoulig@unipi.gr](cdoulig@unipi.gr)  \narXiv :2603 . 177 17v4 [ cs .CR] 10 Jul 2026  \nAbstract—Supervised detection of network attacks has always been a critical part of network intrusion detection systems (NIDS). Nowadays, in a pivotal time for artificial intelligence (AI), with even more sophisticated attacks that utilize advanced techniques, such as generative artificial intelligence (GenAI) and reinforcement learning, it has become a vital component if we wish to protect our personal data, which are scattered across the web. In this paper, we address two tasks, in the first unified multi-modal NIDS dataset, which incorporates flow-level data, packet payload information and temporal contextual features, from the reprocessed CIC-IDS-2017, CIC-IoT-2023, UNSW-NB15 and CIC-DDoS-2019, with the same feature space. In the first task we use machine learning (ML) algorithms, with stratified cross validation, in order to prevent network attacks, with stability and reliability. In the second task we use adversarial learning algorithms to generate synthetic data, compare them with the real ones and evaluate their fidelity, utility and privacy using the SDV framework, f-divergences, distinguishability and non-parametric statistical tests. The findings provide stable ML models for intrusion detection and generative models with high fidelity and utility, by combining the Synthetic Data Vault framework, the TRTS and TSTR tests, with non-parametric statistical tests and f-divergence measures.  \nIndex Terms—Machine learning (ML), artificial intelligence (AI), generative artificial intelligence (GenAI), network intrusion detection systems (NIDS), Unified Multimodal Network Intrusion Detection System (UMNIDS), generative adversarial networks (GANs).  \nI. INTRODUCTION  \nIn the era of AI, detecting the type of the attack becomeseven more difficult. Machine learning algorithms have been implemented in many research papers and application areas [10] showing efficiency in tackling attacks across a variety of well-known intrusion detection system (IDS) datasets [38],[24], [29], [30], [32] . Nevertheless, it is necessary to not simply focus on achieving high results in classification metrics, but offering reliability and stability to an intrusion detection system.  \nIn the last few years adversarial attacks have gained popularity due to their sophisticated attacks, that utilize adversarial machine learning algorithms to inject perturbations in the data,  \nin order to make a strong classifier unable to classify certain attacks correctly, thus misleading the IDS.  \nMany types of algorithms, from linear models and SVM to neural networks and reinforcement learning have been proposed in [5] . Commonly used algorithms in IoT tabular data are logistic regression as a baseline for multi-class classification as well as more advanced models like deep neural networks and ensemble models [9] . More detailed studies have examined cross-dataset validation with LDA, Xgboost and decision trees [24] . Different frameworks have been widely used for data generation purposes like Synthcity [40] and SDV [26],[8] offering high quality generators and evaluating metrics. The attention of researchers has recently been directed in many conditional architectures for synthetic network data generation for GANs and VAEs [20],[21],[22],[25],[27],[31], as well as in the emerging f-GANs and diffusion models [6], [12], [39] with the LLMs being top-tier models [37] . Furthermore, the specific non-parametric statistical tests, for means, covariance matrices and multivariate distribution comparison, have been used in some papers consider","cbCaigpZ52KWTlv5","https://ap.wps.com/l/cbCaigpZ52KWTlv5","pdf",435290,4,1,7,"English","en",105,"# Introduction\n## Machine Learning-Based NIDS Methodology\n### Data Collection\n## Attack Classification and Evaluation\n## Synthetic Data Generation and Evaluation","[{\"question\":\"What are the two main tasks addressed in the paper?\",\"answer\":\"The paper performs (1) supervised attack classification for NIDS using machine learning models and (2) synthetic data generation using adversarial learning, followed by evaluation of fidelity, utility and privacy.\"},{\"question\":\"Which datasets are used to build the unified multimodal dataset?\",\"answer\":\"The study uses reprocessed CIC-IDS-2017, CIC-IoT-2023, UNSW-NB15 and CIC-DDoS-2019, incorporated into a unified multi-modal NIDS dataset with flow-level data, packet payload information and temporal contextual features.\"},{\"question\":\"How are generated synthetic data and privacy evaluated?\",\"answer\":\"Synthetic data are assessed with the SDV framework, including f-divergences and distinguishability, and privacy is measured alongside non-parametric statistical tests comparing multivariate characteristics such as means, covariance matrices, and joint feature distributions.\"}]",1784174794,18,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-for-network-attacks-classification-and-statistical-evaluation-of-adversarial-learning-methodologies-for-synthetic-data-generation","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/machine-learning-for-network-attacks-classification-and-statistical-evaluation-of-adversarial-learning-methodologies-for-synthetic-data-generation/81616/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What are the two main tasks addressed in the paper?","Question",{"text":75,"@type":76},"The paper performs (1) supervised attack classification for NIDS using machine learning models and (2) synthetic data generation using adversarial learning, followed by evaluation of fidelity, utility and privacy.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which datasets are used to build the unified multimodal dataset?",{"text":80,"@type":76},"The study uses reprocessed CIC-IDS-2017, CIC-IoT-2023, UNSW-NB15 and CIC-DDoS-2019, incorporated into a unified multi-modal NIDS dataset with flow-level data, packet payload information and temporal contextual features.",{"name":82,"@type":73,"acceptedAnswer":83},"How are generated synthetic data and privacy evaluated?",{"text":84,"@type":76},"Synthetic data are assessed with the SDV framework, including f-divergences and distinguishability, and privacy is measured alongside non-parametric statistical tests comparing multivariate characteristics such as means, covariance matrices, and joint feature distributions.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]