[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122984-en":3,"doc-seo-122984-105":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":4,"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":27,"seo_description":14,"update_tm":28,"read_time":29},122984,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Towards Sustainable SecureML - Quantifying Carbon Footprint of Adversarial Machine Learning","Widespread machine learning adoption raises sustainability concerns due to high energy consumption and carbon emissions, which becomes even more urgent in adversarial ML. Defenses against network-based attacks often require additional computation and security measures, intensifying environmental impact. This work investigates adversarial ML’s carbon footprint and provides empirical evidence linking stronger adversarial robustness to higher emissions. To quantify this trade-off, it introduces the Robustness Carbon Trade-off Index (RCTI), validated via evasion-attack experiments analyzing robustness, performance, and emissions.","Towards Sustainable SecureML: Quantifying Carbon Footprint of Adversarial Machine Learning  \nSyed Mhamudul Hasan 1 ,2 , Abdur R. Shahid 1 ,2 , Ahmed Imteaj 1  \n1 School of Computing, Southern Illinois University, Carbondale, IL, USA  \n2 Secure and Trustworthy Intelligent Systems (SHIELD) Lab  \n[syedmhamudul.hasan@siu.edu](syedmhamudul.hasan@siu.edu), [shahid@cs.siu.edu](shahid@cs.siu.edu), [imteaj@cs.siu.edu](imteaj@cs.siu.edu)  \narXiv :2403 . 19009v1 [ cs .LG] 27 Mar 2024  \nAbstract—The widespread adoption of machine learning (ML) across various industries has raised sustainability concerns due to its substantial energy usage and carbon emissions. This issue becomes more pressing in adversarial ML, which focuses on enhancing model security against different network-based attacks. Implementing defenses in ML systems often necessitates additional computational resources and network security measures, exacerbating their environmental impacts. In this paper, we pioneer the first investigation into adversarial ML’s carbon footprint, providing empirical evidence connecting greater model robustness to higher emissions. Addressing the critical need to quantify this trade-off, we introduce the Robustness Carbon Trade-off Index (RCTI). This novel metric, inspired by economic elasticity principles, captures the sensitivity of carbon emissions to changes in adversarial robustness. We demonstrate the RCTI through an experiment involving evasion attacks, analyzing the interplay between robustness against attacks, performance, and carbon emissions.  \nIndex Terms—Adversarial Machine Learning, Carbon Emission, Sustainability, Artificial Intelligence (AI)  \nI. INTRODUCTION  \nIn recent years, the rapid evolution of ML has expanded beyond the tech industry, affecting diverse sectors and heralding a new era of AI-driven innovation. However, the widespread adoption of ML raises environmental concerns due to their significant energy consumption and associated carbon emissions[1], [2] . For instance, training a single advanced language model can emit carbon equivalent to 125 round-trip flights between New York and Beijing[1] . The Information and Communication Technology (ICT) industry, integral to AI, is projected to account for 14% of global emissions[3], emphasizing the urgent need to address ML’s environmental impact.  \nThis research gap is particularly evident in adversarial ML— a domain at the intersection of ML and cybersecurity. Adversarial ML investigates the vulnerabilities of ML systems, crafts attack techniques for exploitation by malicious entities through trusted and untrusted networks, and develops defenses to enhance system resilience. Studies reveal how attackers can manipulate vulnerabilities in various ML phases, launching attacks to degrade model performance or inducing erroneous inferences, as illustrated in figure 1 . An attacker might utilize the network to execute different vulnerable or, sometimes, robust systems with zero-day vulnerabilities. As most systems need networks to communicate with each other, there might be  \nDefense  \nc Data Sanitization, Authentication, Anomaly Detection, Input Validation, Adversarial Training, Differential Privacy, Federated Learning, Cryptographic Techniques, Model Inspection, Model  \nAuditing, Fine-Pruning, Behavioral Analysis  \nFig. 1. Sustainable SecureML: (Adversarial ML landscape) (a) An ML model lifecycle when dealing with data sources hosted on untrusted networks, (b) a classification of the adversarial attacks related to the ML lifecycle phases,(c) various defense mechanisms to defend against adversarial attacks, (d) an illustration of the attacks and their defenses, demonstrating the dynamic interplay of attack and defense tactics in untrusted network settings (figure credit: ART Toolbox[4]), and (e) the scope of our work: the intersection of ML, cybersecurity, and environmental sustainability.  \nsome data alteration when data is transmitted, especially in the data collection phase. ","cbCaifhNgCgk3Dk7","https://ap.wps.com/l/cbCaifhNgCgk3Dk7","pdf",765286,1,6,"English","en",105,"# Introduction\n## Adversarial ML and sustainability concerns\n## Research gap and motivation\n# Contributions\n## Carbon footprint investigation\n## Robustness-Carbon Trade-off Index (RCTI)\n# Experiment and evaluation\n## Evasion attacks and trade-off analysis","[{\"question\":\"What sustainability problem does the paper focus on in adversarial machine learning?\",\"answer\":\"It focuses on the carbon emissions and energy cost introduced when adversarial ML defenses add computational and security overhead.\"},{\"question\":\"What does the paper contribute to quantifying the robustness–emissions trade-off?\",\"answer\":\"It proposes the Robustness Carbon Trade-off Index (RCTI) to measure how changes in adversarial robustness affect carbon emissions.\"},{\"question\":\"How is RCTI evaluated in the paper?\",\"answer\":\"The paper demonstrates RCTI using an experiment with evasion attacks, analyzing relationships among robustness, performance, and carbon emissions.\"}]","Towards Sustainable SecureML - Quantifying Carbon Footprint of Adversarial Machine Learning | PDF",1785814022,15,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"towards-sustainable-secureml-quantifying-carbon-footprint-of-adversarial-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"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/towards-sustainable-secureml-quantifying-carbon-footprint-of-adversarial-machine-learning/122984/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What sustainability problem does the paper focus on in adversarial machine learning?","Question",{"text":75,"@type":76},"It focuses on the carbon emissions and energy cost introduced when adversarial ML defenses add computational and security overhead.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the paper contribute to quantifying the robustness–emissions trade-off?",{"text":80,"@type":76},"It proposes the Robustness Carbon Trade-off Index (RCTI) to measure how changes in adversarial robustness affect carbon emissions.",{"name":82,"@type":73,"acceptedAnswer":83},"How is RCTI evaluated in the paper?",{"text":84,"@type":76},"The paper demonstrates RCTI using an experiment with evasion attacks, analyzing relationships among robustness, performance, and carbon emissions.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":20,"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":53,"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":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"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"]