{"id":"https://openalex.org/W7165879838","doi":"https://doi.org/10.48550/arxiv.2606.25239","title":"Tensor-Based Batch Fuzzing with Adaptive Perturbation Scaling for Deep Neural Networks","display_name":"Tensor-Based Batch Fuzzing with Adaptive Perturbation Scaling for Deep Neural Networks","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7165879838","doi":"https://doi.org/10.48550/arxiv.2606.25239"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.25239","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25239","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.25239","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008760836","display_name":"Guanqin Zhang","orcid":"https://orcid.org/0000-0002-3844-8180"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Guanqin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139351225","display_name":"Yulei Sui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sui, Yulei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.49729999899864197,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.49729999899864197,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.24070000648498535,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.033399999141693115,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fuzz-testing","display_name":"Fuzz testing","score":0.916100025177002},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5198000073432922},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.4657000005245209},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4643999934196472},{"id":"https://openalex.org/keywords/counterexample","display_name":"Counterexample","score":0.46309998631477356},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4629000127315521},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.4255000054836273},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3993000090122223}],"concepts":[{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.916100025177002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6577000021934509},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4643999934196472},{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4047999978065491},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.38040000200271606},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3497999906539917},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3255999982357025},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3077999949455261},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.275299996137619},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.25239","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25239","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.25239","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25239","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2,213],"are":[3],"increasingly":[4],"deployed":[5],"in":[6,164,191,249],"safety-critical":[7],"domains":[8],"such":[9],"as":[10,127,133,179],"autonomous":[11],"driving":[12],"and":[13,48,67,113,171,200,214,221,232],"medical":[14],"diagnosis,":[15],"yet":[16],"their":[17],"opaque,":[18],"high-dimensional":[19],"parameter":[20],"spaces":[21,154],"make":[22],"it":[23],"difficult":[24],"to":[25,228],"systematically":[26],"assess":[27],"model":[28,185],"reliability":[29],"on":[30,92,208],"unseen":[31],"inputs.":[32],"Existing":[33],"coverage-guided":[34],"sequential":[35,238],"fuzzing":[36,47,79,198,225],"frameworks":[37],"for":[38],"DNNs":[39],"inherit":[40],"a":[41,75,93,117,128,147,183,192],"one-input-per-iteration":[42],"design":[43],"from":[44,105],"traditional":[45],"software":[46],"apply":[49],"uniform":[50],"perturbation":[51,83,96],"budgets":[52],"across":[53,161,218],"all":[54,162],"input":[55,153,169],"dimensions,":[56],"limiting":[57],"both":[58,87],"testing":[59],"throughput":[60,231],"(i.e.,":[61],"inputs":[62],"processed":[63],"per":[64],"unit":[65],"time)":[66],"the":[68,142,149,165,177,237,241],"precision":[69],"of":[70],"input-space":[71],"exploration.":[72,202],"We":[73,167,203],"present":[74],"new":[76],"specification-aware":[77],"batch":[78],"framework":[80,206],"with":[81,141,155],"adaptive":[82],"scaling":[84,122],"that":[85,186],"addresses":[86],"limitations.":[88],"Rather":[89],"than":[90,236],"relying":[91],"fixed":[94],"global":[95,129],"radius":[97],"epsilon,":[98],"our":[99,205],"approach":[100],"derives":[101],"mutation":[102],"step":[103,135],"sizes":[104,136],"specification-defined":[106],"feasible":[107],"ranges":[108],"(the":[109],"gap":[110],"between":[111],"lower":[112],"upper":[114],"bounds)":[115],"using":[116],"shared":[118],"scale":[119],"factor.":[120],"This":[121],"can":[123,151],"be":[124],"applied":[125],"either":[126],"scalar":[130],"(isotropic)":[131],"or":[132],"per-dimension":[134],"(anisotropic),":[137],"keeping":[138],"perturbations":[139],"consistent":[140],"underlying":[143],"constraint":[144],"structure.":[145],"As":[146],"result,":[148],"fuzzer":[150],"explore":[152],"heterogeneous":[156],"feature":[157],"scales":[158],"more":[159,234],"effectively":[160],"specifications":[163,217],"batch.":[166],"embed":[168],"constraints":[170],"output":[172],"property":[173],"checks":[174],"directly":[175],"into":[176],"network":[178],"non-trainable":[180],"layers,":[181],"yielding":[182],"wrapped":[184],"processes":[187],"B":[188],"specification":[189],"instances":[190],"single":[193],"batched":[194],"iteration,":[195],"substantially":[196],"improving":[197],"efficiency":[199],"counterexample":[201],"evaluate":[204],"extensively":[207],"three":[209],"benchmarks,":[210],"covering":[211],"six":[212],"over":[215],"400":[216],"TrafficSigns,":[219],"Cifar100,":[220],"TinyImageNet.":[222],"Our":[223],"tensor-based":[224],"achieves":[226],"up":[227],"40X":[229],"higher":[230],"4X":[233],"violations":[235],"baseline":[239],"under":[240],"same":[242],"time":[243],"budget,":[244],"demonstrating":[245],"significantly":[246],"improved":[247],"effectiveness":[248],"specification-guided":[250],"fuzzing.":[251]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-26T00:00:00"}