[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86618-en":3,"doc-seo-86618-105":30,"detail-sidebar-cat-0-en-105":92},{"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},86618,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Deceiving Post-hoc Explainable AI (XAI) Methods in Network Intrusion Detection","Artificial Intelligence in future networks faces scrutiny due to biases, misclassifications, and security threats. Explainable AI (XAI) aims to expose hidden biases in black-box AI/ML used for network operations, yet scaffolding attacks can conceal internal bias from XAI and disrupt monitoring, security services, regulators, auditors, and end-users, including Intent-Based Networking (IBN). The work formalizes an attacker framework for Network Intrusion Detection Systems (NIDS), proposes an auditor detection method, validates it on NSL-KDD, and simulates it on 5G data.","Deceiving Post-hoc Explainable AI (XAI) Methods in Network Intrusion Detection  \nThulitha Senevirathna∗ , Bartlomiej Siniarski†, Madhusanka Liyanage‡, Shen Wang§∗†‡§ School of Computer Science, University College Dublin, Ireland  \nEmail:∗[thulitha.senevirathna@ucdconnect.ie](thulitha.senevirathna@ucdconnect.ie),†bartlomiej.siniarski@ucd.ie,‡[madhusanka@ucd.ie](madhusanka@ucd.ie),§[shen.wang@ucd.ie](shen.wang@ucd.ie)  \nAbstract—Artificial Intelligence used in future networks is vulnerable to biases, misclassifications, and security threats, which seeds constant scrutiny in accountability. Explainable AI (XAI) methods bridge this gap in identifying unaccounted biases in black-box AI/ML models. However, scaffolding attacks would hide the internal biases of the model from XAI methods, jeopardizing any auditory or monitoring processes, service provisions, security systems, regulators, auditors, and end-users in future networking paradigms, including Intent-Based Networking (IBN). For the first time ever, we formalize and demonstrate a framework on how an attacker would adopt scaffoldings to deceive the security operators in Network Intrusion Detection Systems (NIDS). Furthermore, we propose a detection method that auditors can use to detect the attack efficiently. We rigorously test the attack and detection methods using the NSL-KDD. We then simulate the attack on 5G network data. Our simulation illustrates that the attack adoption method is successful, and the detection method can identify an affected model with extremely high confidence.  \nIndex Terms—Explainable security, 5G, B5G, Network Intrusion Detection, Machine Learning, Scaffolding Attack, Future networks, Intent-based networks  \nI. INTRODUCTION  \nFast-changing networking technologies like Machine Learning (ML), and Artificial Intelligence (AI) demand accountability and trustworthiness. Network Intrusion Detection System (NIDS)s are rapidly becoming popular to use AI/ML techniques [1], [2] and are already available for purchase from third-party companies. This trend is appealing to networking organizations as they can save costs and focus their full strengths on the core products. However, for proprietary reasons, such models are purposely turned into black boxes (e.g., tree-based models) to conceal model knowledge from rivals. OpenAI’s refusal to provide GPT-4’s architecture foreshadows such a trend [3] . In recent research, Explainable AI (XAI) has become an X-ray on the black-box NIDS models to increase their transparency. In-house red/blue teams, independent security auditors, and regulatory authorities can utilize XAI with minimal programming abilities [4] . However, it has been recently brought to light that scaffolding attacks [5] can deceive even the XAI methods, making the clients vulnerable  \nThis research is a part of the SPATIAL project that has received funding from the European Union’s Horizon 2020 research and innovation program under the grant agreement No.101021808 and CONNECT phase 2 project that has received funding from Science Foundation Ireland under grant no. 13/RC/2077 P2 .  \nto external attacks. A model creator would be enticed to embed a scaffolding in an AI model for several reasons: to undermine competitors through bias, to enable later access through backdoors [6], [7], and by disgruntled employees. Considering the wide variety of usage of post-hoc XAI methods, a deceptive AI model deployed by an attacker could cause a devastating effect. For instance, when explanations are fed back to the AI model to improve the accuracy from the client side training [8], [9] . Wrong explanations, multiplied over many feedback iterations, can degrade or even create back-doors for future attacks.  \nSo far, this attack is only known to be used in sociocultural instances. With our work, we also extend the attack’s applicability to the networking domain.  \nA. Related work  \nThe work such as [9]–[11] bring to light the potential of XAI in the context of Intrusion ","cbCaif0VTneZQStN","https://ap.wps.com/l/cbCaif0VTneZQStN","pdf",817570,6,1,7,"English","en",105,"# Introduction\n## Related work\n## Contributions\n# Attack and Detection Framework","[{\"question\":\"What problem does the paper address in explainable AI for network intrusion detection?\",\"answer\":\"The paper addresses how post-hoc explainable AI (XAI) can be deceived when an attacker uses scaffolding to hide internal biases from XAI outputs used by security operators and auditors.\"},{\"question\":\"What contributions are proposed for attackers and auditors?\",\"answer\":\"It formalizes and demonstrates an attacker framework that adopts scaffoldings to mislead NIDS security operations, and it proposes an auditor-facing detection method to efficiently identify the affected model.\"},{\"question\":\"How is the approach validated, and what do the simulations show?\",\"answer\":\"The attack and detection methods are rigorously tested using NSL-KDD and then simulated on 5G network data. Results indicate the attack method succeeds and the detection method identifies the impacted model with extremely high confidence.\"}]",1784236227,18,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"deceiving-post-hoc-explainable-ai-xai-methods-in-network-intrusion-detection","",{"@graph":36,"@context":86},[37,54,69],{"@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":53},"https://docshare.wps.com/document/deceiving-post-hoc-explainable-ai-xai-methods-in-network-intrusion-detection/86618/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-30","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the paper address in explainable AI for network intrusion detection?","Question",{"text":76,"@type":77},"The paper addresses how post-hoc explainable AI (XAI) can be deceived when an attacker uses scaffolding to hide internal biases from XAI outputs used by security operators and auditors.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What contributions are proposed for attackers and auditors?",{"text":81,"@type":77},"It formalizes and demonstrates an attacker framework that adopts scaffoldings to mislead NIDS security operations, and it proposes an auditor-facing detection method to efficiently identify the affected model.",{"name":83,"@type":74,"acceptedAnswer":84},"How is the approach validated, and what do the simulations show?",{"text":85,"@type":77},"The attack and detection methods are rigorously tested using NSL-KDD and then simulated on 5G network data. Results indicate the attack method succeeds and the detection method identifies the impacted model with extremely high confidence.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"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":107,"slug":137},19,"General","general"]