[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-513100-105":59,"doc-detail-513100-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","learning-bounded-rationality-models-of-the-adversary-in-repeated-stackelberg-security-games-abstract","Learning Bounded Rationality Models of the Adversary in Repeated Stackelberg Security Games - Abstract","","Several competing human behavior models target boundedly rational adversaries in repeated Stackelberg security games, yet they underperform due to three critical gaps. They ignore adversary adaptation driven by successes and failures of past attack actions, they assume early-round data volume suffices despite limited exposure of the attack surface, and they omit probability weighting functions despite nonlinear human probability weighting. The paper introduces SHARP to model adaptiveness using observed success/failure, discount unexposed attack areas, and incorporate a nonlinear probability weighting function, plus compares learning approaches and reports a longitudinal multi-week study of competing 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/learning-bounded-rationality-models-of-the-adversary-in-repeated-stackelberg-security-games-abstract/513100/",{"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/learning-bounded-rationality-models-of-the-adversary-in-repeated-stackelberg-security-games-abstract/513100.png","ImageObject",300,407,{"name":92,"@type":93},"LangkahRina","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-16","2026-10-06",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why do existing bounded rationality models perform poorly in repeated Stackelberg security games?","Question",{"text":113,"@type":114},"They fail to account for adversary adaptation from the success or failure of past attacks, assume early-round data volume guarantees model reliability despite limited attack-surface exposure, and neglect nonlinear probability weighting functions that humans typically use.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What does SHARP add to address adversary adaptiveness in the game?",{"text":118,"@type":114},"SHARP models adaptiveness by reasoning over success or failure of adversary past actions on exposed parts of the attack surface, capturing how future behavior changes based on those outcomes.",{"name":120,"@type":111,"acceptedAnswer":121},"How does SHARP handle limited exposure to the attack surface and probability weighting?",{"text":122,"@type":114},"It reasons about similarity between exposed and unexposed areas and uses a discounting parameter to mitigate insufficient exposure. It also integrates a nonlinear probability weighting function to reflect the adversary’s true probability weighting.","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},513100,1791383166,{"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":44,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":19,"preview_urls":146},962090893776,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Learning Bounded Rationality Models of the Adversary in  \nRepeated Stackelberg Security Games􀀃  \nDebarun Kar, Fei Fang, Francesco Delle Fave􀀃 , Nicole Sintov, Arunesh Sinha, Aram  \nGalstyan, Bo An+ , Milind Tambe  \nUniversity of Southern California, Los Angeles, CA, 90089  \n􀀃 Disney Research, Boston, MA, 02142 + Nanyang Technological University, Singapore, 639798  \n{dkar,feifang,sintov,aruneshs,galstyan,[tambe}@usc.edu](tambe}@usc.edu),  \n􀀃 [francesco.dellefave@disneyresearch.com](francesco.dellefave@disneyresearch.com), + [boan@ntu.edu.sg](boan@ntu.edu.sg)  \nABSTRACT  \nSeveral competing human behavior models have been proposed to model and protect against boundedly rational adversaries in repeated Stackelberg security games (SSGs) . However, these existing models fail to address three main issues which are extremely detrimental to defender performance. First, while they attempt to learn adversary behavior models from adversaries' past actions (“attackson targets”), they fail to take into account adversaries' future adaptation based on successes or failures of these past actions. Second, they assume that sufﬁcient data in the initial rounds will lead toa reliable model of the adversary. However, our analysis reveals that the issue is not the amount of data, but that there just is not enough of the attack surface exposed to the adversary to learn a reliable model. Third, current leading approaches have failed to include probability weighting functions, even though it is well known that human beings' weighting of probability is typically nonlinear. Moreover, the performances of these models may be critically dependent on the learning algorithm used to learn the parameters of these models. The ﬁrst contribution of this paper is a new human behavior model, SHARP, which mitigates these three limitations as follows: (i) SHARP reasons based on success or failure of the adversary's past actions on exposed portions of the attack surface to model adversary adaptiveness; (ii) SHARP reasons about similarity between exposed and unexposed areas of the attack surface, and also incorporates a discounting parameter to mitigate adversary's lack of exposure to enough of the attack surface; and (iii) SHARP integrates a non-linear probability weighting function to capture the adversary's true weighting of probability. Our second contribution is a comparison of two different approaches for learning the parameters of the bounded rationality models.  \nOur third contribution is a ﬁrst “longitudinal study” – at least in the context of SSGs – of competing models in settings involving repeated interaction between the attacker and the defender. This study, where each experiment lasted a period of multiple weeks with individual sets of human subjects, illustrates the strengths and weaknesses of different models and shows the advantages of SHARP.  \n1. INTRODUCTION  \nWhereas previous real-world deployments of Stackelberg Security Games (SSGs) to protect airports, ports or ﬂights have been one-shot game models [29], recent work has focused on domains involving repeated interactions between defenders and adversaries.  \n􀀃 This paper is based on the following AAMAS'15 full paper- \"A Game of Thrones\": When Human Behavior Models Compete in Repeated Stackelberg Security Games. The second contribution mentioned in the abstract and discussed later in the paper along with detailed experimental results is a new contribution as compared to the AAMAS'15 paper.  \nThese domains include security of wildlife (repeated interactions between rangers and poachers) [31], security of ﬁsheries (repeated interactions between coast guard and illegal ﬁshermen) [10], forest protection or drug interdiction, and are modeled via repeated SSGs. In a repeated SSG model, the defender periodically deploys new patrol strategies (in “rounds” of the game) and the adversary observes these strategies and acts accordingly.  \nResearch in repeated SSGs has produced different approaches to address unc","cbCaiobMeMQsaTGa","https://ap.wps.com/l/cbCaiobMeMQsaTGa","pdf",1506200,"English","# Abstract\n## Key limitations in existing bounded rationality models\n## SHARP model contributions\n## Comparative learning approaches\n## Longitudinal study in repeated interaction settings\n# Introduction\n## One-shot vs repeated Stackelberg security game deployments\n## Research directions and assumptions\n## Three key limitations affecting defender performance","[{\"question\":\"Why do existing bounded rationality models perform poorly in repeated Stackelberg security games?\",\"answer\":\"They fail to account for adversary adaptation from the success or failure of past attacks, assume early-round data volume guarantees model reliability despite limited attack-surface exposure, and neglect nonlinear probability weighting functions that humans typically use.\"},{\"question\":\"What does SHARP add to address adversary adaptiveness in the game?\",\"answer\":\"SHARP models adaptiveness by reasoning over success or failure of adversary past actions on exposed parts of the attack surface, capturing how future behavior changes based on those outcomes.\"},{\"question\":\"How does SHARP handle limited exposure to the attack surface and probability weighting?\",\"answer\":\"It reasons about similarity between exposed and unexposed areas and uses a discounting parameter to mitigate insufficient exposure. It also integrates a nonlinear probability weighting function to reflect the adversary’s true probability weighting.\"}]","Learning Bounded Rationality Models of the Adversary in Repeated Stackelberg Security Games - Abstract | PDF",1791280035,23,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/68d88ab5ee76e1854acf7dd756cb4702.webp",983,1272,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/07862e8e7d1a8f86a859e999669a9c31.webp",982,1270,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/3f01de5c9e5b2772fa3d8c781a378891.webp",981,1269,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/dc12da4916d64c36530baca575d12645.webp",980,1268]