[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85502-en":3,"doc-seo-85502-105":29,"detail-sidebar-cat-0-en-105":90},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},85502,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","HyperNet Adaptation for Diffusion-Based Test Case Generation","Deep learning deployment demands reliable evaluation under real-world input variations and realistic failure behaviors. Gradient-based adversarial attacks often yield imperceptible perturbations that emphasize robustness more than functional failure. Generative test generation can better reflect realistic scenarios, but diffusion-model testing is hindered by high computational cost and weak controllability at scale. HyNeA introduces dataset-free controllability via hypernetworks, enabling instance-level tuning to target failure-inducing cases without dataset-dependent fine-tuning, improving diversity and controllability while generalizing when failure-labeled data is absent.","arXiv :2601 . 1504 1v2 [ cs .LG] 13 Jul 2026  \nHyperNet-Adaptation for Diffusion-Based Test Case Generation  \nOLIVER WEISSL, Technical University of Munich, Germany VINCENZO RICCIO, University of Udine, Italy SEVERIN KACIANKA, Independent Researcher, Germany  \nANDREA STOCCO, Technical University of Munich, Germany and fortiss GmbH, Germany  \nThe increasing deployment of deep learning systems requires systematic evaluation of their reliability in real-world scenarios. Traditional gradient-based adversarial attacks introduce small perturbations that rarely correspond to realistic failures and mainly assess robustness rather than functional behavior. Generative test generation methods offer an alternative but are often limited to simple datasets or constrained input domains. Although diffusion models enable high-fidelity image synthesis, their computational cost and limited controllability restrict their applicability to large-scale testing. We present HyNeA, a generative testing method that enables direct and efficient control over diffusion-based generation. HyNeA provides dataset-free controllability through hypernetworks, allowing targeted manipulation of the generative process without relying on architecture-specific conditioning mechanisms or dataset-driven adaptations such as fine-tuning. HyNeA employs a distinct training strategy that supports instance-level tuning to identify failure-inducing test cases without requiring datasets that explicitly contain examples of similar failures. This approach enables the targeted generation of realistic failure cases at substantially lower computational cost than search-based methods. Experimental results show that HyNeA improves controllability and test diversity compared to existing generative test generators and generalizes to domains where failure-labeled training data is unavailable.  \nCCS Concepts: • Computing methodologies → Machine learning; • Software and its engineering → Software creation and management.  \nAdditional Key Words and Phrases: DL testing, Diffusion Models, Generative AI  \nACM Reference Format:  \nOliver Weißl, Vincenzo Riccio, Severin Kacianka, and Andrea Stocco. 2026. HyperNet-Adaptation for DiffusionBased Test Case Generation. 1, 1 (July 2026), 34 pages. [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \n1 Introduction  \nDeep learning (DL) models have become central to a wide range of vision applications, from object recognition, classification and segmentation to autonomous systems [43] . As these models are increasingly deployed in real-world settings, evaluating their reliability to input variations and realistic scenarios becomes critical. Traditional gradient-based adversarial attacks can reveal vulnerabilities but generate perturbations that are imperceptible and may be unrealistic, failing to anticipate the diverse set of failures that may occur during operation [4, 16] . Generative test  \nAuthors’ Contact Information: Oliver Weißl, [o.weissl@tum.de](o.weissl@tum.de), Technical University of Munich, Garching near Munich, Germany; Vincenzo Riccio, [vincenzo.riccio@uniud.it](vincenzo.riccio@uniud.it), University of Udine, Udine, Italy; Severin Kacianka, severin.kacianka@ [gmail.com](gmail.com), Independent Researcher, Germany; Andrea Stocco, [andrea.stocco@tum.de](andrea.stocco@tum.de), Technical University of Munich, Garching near Munich, Germany, stocco@fortiss.org and fortiss GmbH, Munich, Germany.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires [prior specific permission ","cbCairFRYpMZez47","https://ap.wps.com/l/cbCairFRYpMZez47","pdf",20237614,1,34,"English","en",105,"# Introduction\n## Reliability evaluation in real-world deployment\n## Limits of gradient-based adversarial attacks\n## Generative test generation challenges\n## Diffusion models for functional testing\n## Prior work on controllable diffusion","[{\"question\":\"What problem does HyNeA address in diffusion-based test case generation?\",\"answer\":\"HyNeA addresses diffusion models’ high computational cost and limited controllability, which restrict their use for large-scale, realistic functional testing.\"},{\"question\":\"How does HyNeA achieve controllability without dataset-dependent adaptation?\",\"answer\":\"HyNeA uses hypernetworks to provide dataset-free controllability, enabling targeted manipulation of the diffusion generation process without relying on architecture-specific conditioning or dataset-driven fine-tuning.\"},{\"question\":\"What training approach does HyNeA use to find failure-inducing test cases?\",\"answer\":\"HyNeA employs a distinct training strategy that supports instance-level tuning to identify failure-inducing test cases without needing datasets that explicitly contain examples of similar failures.\"}]",1784204047,86,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"hypernet-adaptation-for-diffusion-based-test-case-generation","",{"@graph":35,"@context":84},[36,53,67],{"@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/hypernet-adaptation-for-diffusion-based-test-case-generation/85502/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does HyNeA address in diffusion-based test case generation?","Question",{"text":74,"@type":75},"HyNeA addresses diffusion models’ high computational cost and limited controllability, which restrict their use for large-scale, realistic functional testing.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does HyNeA achieve controllability without dataset-dependent adaptation?",{"text":79,"@type":75},"HyNeA uses hypernetworks to provide dataset-free controllability, enabling targeted manipulation of the diffusion generation process without relying on architecture-specific conditioning or dataset-driven fine-tuning.",{"name":81,"@type":72,"acceptedAnswer":82},"What training approach does HyNeA use to find failure-inducing test cases?",{"text":83,"@type":75},"HyNeA employs a distinct training strategy that supports instance-level tuning to identify failure-inducing test cases without needing datasets that explicitly contain examples of similar failures.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]