[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85252-en":3,"doc-seo-85252-105":29,"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85252,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Automated Stealthy Wear Out Attack on Digital Twins With Deep Reinforcement Learning","Digital Twins (DTs) enable Industry 4.0 by unifying real-time monitoring, simulation, and control across physical and virtual domains, but this integration enlarges the industrial attack surface. The work presents a stealthy wear-out attack driven by Deep Reinforcement Learning (DRL) that covertly manipulates control signals to raise torque on a targeted joint and accelerate degradation while evading state-of-the-art anomaly detection. Benchmarks show SAC achieves the best sample efficiency, stability, and attack effectiveness. Experiments on a UR10e robotic arm confirm stealthy torque elevation, higher maintenance costs, and the need for robust defenses.","This paper has been accepted to appear in the IEEE European Symposium on Security and Privacy (Euro S&P), 2026 .  \nAutomated Stealthy Wear-Out Attack on Digital Twins With Deep Reinforcement  \nLearning  \nJoshua Haworth⊠ , Aryan Pasikhani, George Pavlides, Prosanta Gope, John Clark Department of Computer Science, University of Sheffield, United Kingdom {jhaworth1, aryan.pasikhani, p.gope, john.clark}@sheffield.ac.uk, p-george18@hotmail.com  \narXiv :2607 . 10830v 1 [ cs .CR] 12 Jul 2026  \nAbstract—Digital Twins (DTs) have emerged as pivotal enablers of Industry 4.0, offering transformative capabilities such as real-time monitoring, advanced simulation, and precise control of physical assets. By bridging the physical and virtual domains, DTs facilitate seamless integration of data-driven decision-making and operational optimisation. However, this seamless interaction significantly expands the attack surface of industrial systems, creating vulnerabilities that adversaries can exploit. This paper introduces a novel and stealthy wear-out attack leveraging Deep Reinforcement Learning (DRL) to target DT-enabled infrastructures. The adversary strategically and covertly manipulates control signals, inducing increased torque on a specific joint to accelerate wear and tear while evading detection by a stateof-the-art anomaly detection system. Extensive benchmarking of reinforcement learning algorithms - including Twin Delayed Deep Deterministic Policy Gradient (TD3), Soft Actor-Critic (SAC), Proximal Policy Optimisation (PPO), and Advantage Actor-Critic (A2C) - revealed that SAC consistently outperformed its counterparts in terms of sample efficiency, stability, and overall attack effectiveness. We evaluate the proposed adversary in an industrial setting using the UR10e robotic arm. Results demonstrate the adversary’s ability to significantly elevate torque levels on the targeted joint, leading to accelerated degradation and increased maintenance costs, all while operating stealthily and avoiding detection. Our findings highlight the substantial risks posed by DRL-driven adversaries to DT-enabled environments and emphasise the critical need for robust defence mechanisms to protect critical industrial systems.  \nIndex Terms—Digital Twins, Reinforcement Learning, Adversarial Machine Learning  \n1. Introduction  \nStriving to realise the Industry 4.0 vision represents one of the top priorities for manufacturers* . The use of industrial robots, cloud computing and vast amounts of sensor data collected throughout a product’s lifecycle are expected to improve production efficiency, flexibility and decision making, while at the same time reducing waste and minimising carbon emissions [1], [2] . Digital Twin (DT) technology is one of the vital enablers for the realisation of Industry 4.0 [2] . It provides a virtual replica of a physical entity, system or process, that gets updated in real-time according to past data, real-time  \n*[https://www.sap.com/products/scm/industry-4-0/](https://www.sap.com/products/scm/industry-4-0/)[ ](https://www.sap.com/products/scm/industry-4-0/)[industry-4-0-strategy.html](industry-4-0-strategy.html)  \nsensor readings and a predefined physical model [2] . DTs seamlessly integrate and analyse physical and digital data recorded throughout a product’s lifecycle, providing new services which can be utilised to adjust how an operation is performed in the physical space according to direct orders from the virtual space [2] . This can improve the industrial process’ performance, enhance product designsand streamline operations, but also allow for Prognosticsand Health Management (PHM) to detect, in a timely manner, potential asset faults and degradations, thus reducing maintenance costs [2] .  \nTao et al. [3] proposed a five-dimensional model of DTin which there is a clear separation between the elements involved. Specifically, the DT architecture is decomposed into Physical Entity (PE), Virtual Entity (VE), Services (Ss), DT","cbCaiq9fYqrxu6gh","https://ap.wps.com/l/cbCaiq9fYqrxu6gh","pdf",866323,1,17,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What kind of attack does the paper propose against digital-twin systems?\",\"answer\":\"It introduces an automated stealthy wear-out attack that uses Deep Reinforcement Learning to manipulate control signals and accelerate physical degradation of a targeted joint.\"},{\"question\":\"How does the attack avoid detection?\",\"answer\":\"The adversary strategically induces increased torque while evading a state-of-the-art anomaly detection system.\"},{\"question\":\"Which reinforcement learning algorithm performed best in the experiments?\",\"answer\":\"Soft Actor-Critic (SAC) consistently outperformed TD3, PPO, and A2C in sample efficiency, stability, and overall attack effectiveness.\"}]",1784202096,43,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"automated-stealthy-wear-out-attack-on-digital-twins-with-deep-reinforcement-learning","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/automated-stealthy-wear-out-attack-on-digital-twins-with-deep-reinforcement-learning/85252/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","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 kind of attack does the paper propose against digital-twin systems?","Question",{"text":75,"@type":76},"It introduces an automated stealthy wear-out attack that uses Deep Reinforcement Learning to manipulate control signals and accelerate physical degradation of a targeted joint.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the attack avoid detection?",{"text":80,"@type":76},"The adversary strategically induces increased torque while evading a state-of-the-art anomaly detection system.",{"name":82,"@type":73,"acceptedAnswer":83},"Which reinforcement learning algorithm performed best in the experiments?",{"text":84,"@type":76},"Soft Actor-Critic (SAC) consistently outperformed TD3, PPO, and A2C in sample efficiency, stability, and overall attack effectiveness.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]