[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-31794":3,"doc-seo-31794":26},{"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,"file_id":15,"file_url":16,"file_type":17,"file_size":18,"view_count":4,"is_deleted":4,"is_public":19,"is_downloadable":19,"audit_status":19,"page_count":11,"language":20,"language_code":21,"table_of_contents":22,"faqs":23,"seo_title":13,"seo_description":14,"update_tm":24,"read_time":25},31794,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","A Study on Prompt Injection Attack Against LLM Integrated Mobile Robotic Systems","Integration of Large Language Models (LLMs) such as GPT-4o into robotic platforms advances embodied artificial intelligence by enabling multimodal prompt understanding and more context-aware decisions. In mobile robotic navigation, however, security vulnerabilities emerge as adversarial multimodal inputs can mislead models and trigger unsafe or incorrect navigation. This study evaluates prompt injection attacks on LLM-integrated mobile robotic systems and develops secure prompt strategies to reduce these risks. Results show about a 30.8% overall improvement in attack detection and system performance using robust defenses.","cbCaif82gbDulRMz","https://ap.wps.com/l/cbCaif82gbDulRMz","pdf",1230774,1,"English","en","# Introduction\n# Related Works","[{\"question\":\"Why do prompt injection attacks matter for LLM-integrated mobile robots?\",\"answer\":\"Prompt injection attacks can exploit vulnerabilities in multimodal prompting, causing the robot to produce incorrect or dangerous navigation decisions that affect both the robot and its surroundings.\"},{\"question\":\"What system and attack scope does the study investigate?\",\"answer\":\"The study deploys an LLM-controlled mobile robot in simulation and investigates its robustness against prompt injection attacks, including how GPT-4o handles such attacks.\"},{\"question\":\"How do the proposed defense mechanisms improve performance?\",\"answer\":\"Implementing robust defense mechanisms via secure prompting strategies improves both attack detection and overall system performance by approximately 30.8%.\"}]",1780174820,20,{"code":4,"msg":27,"data":28},"ok",{"site_id":29,"language":21,"slug":30,"title":13,"keywords":31,"description":14,"schema_data":32,"social_meta":83,"head_meta":85,"extra_data":87,"updated_unix":24},105,"a-study-on-prompt-injection-attack-against-llm-integrated-mobile-robotic-systems","",{"@graph":33,"@context":82},[34,51,65],{"@type":35,"itemListElement":36},"BreadcrumbList",[37,41,45,48],{"item":38,"name":39,"@type":40,"position":19},"https://docshare.wps.com","Home","ListItem",{"item":42,"name":43,"@type":40,"position":44},"https://docshare.wps.com/document/","Document",2,{"item":46,"name":12,"@type":40,"position":47},"https://docshare.wps.com/document/research-report/",3,{"item":49,"name":13,"@type":40,"position":50},"https://docshare.wps.com/document/a-study-on-prompt-injection-attack-against-llm-integrated-mobile-robotic-systems/31794/",4,{"url":49,"name":13,"@type":52,"author":53,"headline":13,"publisher":55,"fileFormat":58,"description":14,"dateModified":59,"datePublished":59,"encodingFormat":58,"isAccessibleForFree":60,"interactionStatistic":61},"DigitalDocument",{"name":9,"@type":54},"Person",{"url":38,"name":56,"@type":57},"DocShare","Organization","application/pdf","2026-05-30",true,{"@type":62,"interactionType":63,"userInteractionCount":4},"InteractionCounter",{"@type":64},"ViewAction",{"@type":66,"mainEntity":67},"FAQPage",[68,74,78],{"name":69,"@type":70,"acceptedAnswer":71},"Why do prompt injection attacks matter for LLM-integrated mobile robots?","Question",{"text":72,"@type":73},"Prompt injection attacks can exploit vulnerabilities in multimodal prompting, causing the robot to produce incorrect or dangerous navigation decisions that affect both the robot and its surroundings.","Answer",{"name":75,"@type":70,"acceptedAnswer":76},"What system and attack scope does the study investigate?",{"text":77,"@type":73},"The study deploys an LLM-controlled mobile robot in simulation and investigates its robustness against prompt injection attacks, including how GPT-4o handles such attacks.",{"name":79,"@type":70,"acceptedAnswer":80},"How do the proposed defense mechanisms improve performance?",{"text":81,"@type":73},"Implementing robust defense mechanisms via secure prompting strategies improves both attack detection and overall system performance by approximately 30.8%.","https://schema.org",{"og:url":49,"og:type":84,"og:title":13,"og:site_name":56,"og:description":14},"article",{"robots":86,"canonical":49},"index,follow",{"doc_id":7,"site_id":29}]