[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84154-en":3,"doc-seo-84154-105":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},84154,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies","Autonomous negotiation agents are used in high-stakes domains such as insurance and procurement, where users’ private constraints must remain confidential. While cryptography protects explicitly disclosed values, it does not prevent behavioral privacy leakage: adversaries infer constraints from observable dynamics including concession trajectories, timing, and convergence patterns. The paper formalizes behavioral differential privacy for multi-round negotiation protocols and proposes an adaptive randomized policy that achieves (ε,δ)-DP, almost-sure convergence, and high negotiation utility. Experiments on 3,000 synthetic bilateral negotiations reduce inference accuracy by 43–50% while keeping success rates and utility above 90%.","arXiv :2607 .068 15v 1 [ cs .CR] 7 Jul 2026  \nBehavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies  \nBarkha Rani􀀌   \nApple Inc.  \n[barkha_rani@apple.com](barkha_rani@apple.com)  \nAbstract. Autonomous negotiation agents are increasingly deployed in high-stakes settings such as insurance and procurement. While cryptographic techniques protect explicitly disclosed constraint values, they fail to address a subtler threat: behavioral privacy leakage, where an adversary infers private constraints from observable negotiation dynamics such as concession trajectories, timing, and convergence patterns. This paper investigates behavioral differential privacy in multi-round negotiation protocols. We design an adaptive stochastic negotiation policy that jointly guarantees (ε,δ)-differential privacy, almost-sure convergence of the offer sequence (reaching agreement when the counterparty’s reservation value permits), and high negotiation utility. Evaluated on 3,000 synthetic bilateral negotiations, our mechanism reduces adversarial inference accuracy by 43–50% while maintaining a negotiation success rate and utility above 90%, demonstrating that strong privacy guarantees can be achieved without significant loss of performance.  \nKeywords: Differential Privacy · Autonomous Agents · Negotiation · Side-Channel Attacks · Behavioral Privacy  \n1 Introduction  \nLarge language models now power autonomous agents that operate in highstakes negotiation settings, including insurance pricing, procurement contracts, and financial services. These systems act on behalf of users whose private constraints such as maximum budgets or reservation values must remain confidential throughout the negotiation process. Existing defenses leverage cryptographic primitives — including computation sharing protocols, proof-ofknowledge schemes, and lattice-based encryption—to prevent direct exposure of constraint values to opposing parties.  \nHowever, cryptographic protection of explicit data does not address a more subtle threat: the negotiation behavior itself constitutes a side channel. An agent’s offer sequence, concession trajectory, response timing, and convergence speed are all observable by the counterparty, and together they form a rich behavioral trace from which private constraints can be inferred even when the underlying data is cryptographically protected.  \n2 B. Rani  \nConsider a concrete example. Alice employs an autonomous agent to negotiate a health insurance premium, with a private budget of $3,000 . The agent is configured with a zero-knowledge proof preventing the insurer from learning her budget directly. Nevertheless, the agent opens at $2,600, advances to $2,850 in the second round, and reaches $2,950 in the third. The accelerating concession pattern-large early moves tapering toward a sharp plateau-reveals to a sophisticated counterparty that Alice’s true budget is close to $3,000 . No cryptographic mechanism prevents this inference: the information leaks through the structure of the behavior, not through any disclosed value.  \nThis class of vulnerability which we term behavioral privacy leakage has not been formally studied in sequential negotiation systems. Prior work on privacypreserving negotiation focuses exclusively on protecting explicit constraint data, leaving the behavioral side channel unaddressed. Meanwhile, the differential privacy literature, which provides strong formal guarantees against statistical inference, was developed for static database settings and does not transfer directly to multi-round strategic interactions where convergence and utility must also be preserved.  \nThis paper closes that gap. We formalize behavioral differential privacy for sequential negotiation agents, develop a mechanism that provably satisfies (ε,δ)-differential privacy over observable negotiation traces, and prove that the mechanism converges almost surely while preserving high negotiati","cbCaigivzxdcg8b9","https://ap.wps.com/l/cbCaigivzxdcg8b9","pdf",850528,1,18,"English","en",105,"# Abstract\n# Introduction\n## Threat of behavioral privacy leakage\n## Gap and objective\n# Related Work\n## Autonomous negotiation agents\n## Cryptographic privacy in negotiation","[{\"question\":\"What is behavioral privacy leakage in agentic negotiation?\",\"answer\":\"It is the risk that an adversary infers private constraints from observable negotiation behavior—such as concession sequences, timing, and convergence patterns—even when disclosed values are protected cryptographically.\"},{\"question\":\"How does the proposed method protect privacy while negotiating over multiple rounds?\",\"answer\":\"It introduces an adaptive randomized negotiation policy designed to satisfy (ε,δ)-differential privacy over observable offer sequences, using calibration of noise across negotiation phases while preserving feasibility.\"},{\"question\":\"What results does the paper report from experiments?\",\"answer\":\"On 3,000 synthetic bilateral negotiations, the approach reduces adversarial inference accuracy by 43–50% while maintaining negotiation success rate and utility above 90%.\"}]",1784193482,45,{"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},"behavioral-privacy-leakage-in-agentic-negotiation-formalizing-and-mitigating-inference-attacks-via-randomized-policies","",{"@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/behavioral-privacy-leakage-in-agentic-negotiation-formalizing-and-mitigating-inference-attacks-via-randomized-policies/84154/",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 is behavioral privacy leakage in agentic negotiation?","Question",{"text":75,"@type":76},"It is the risk that an adversary infers private constraints from observable negotiation behavior—such as concession sequences, timing, and convergence patterns—even when disclosed values are protected cryptographically.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method protect privacy while negotiating over multiple rounds?",{"text":80,"@type":76},"It introduces an adaptive randomized negotiation policy designed to satisfy (ε,δ)-differential privacy over observable offer sequences, using calibration of noise across negotiation phases while preserving feasibility.",{"name":82,"@type":73,"acceptedAnswer":83},"What results does the paper report from experiments?",{"text":84,"@type":76},"On 3,000 synthetic bilateral negotiations, the approach reduces adversarial inference accuracy by 43–50% while maintaining negotiation success rate and utility above 90%.","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"]