{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:09:27Z","timestamp":1787008167359,"version":"build-2736575974"},"reference-count":64,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000092","name":"U.S. National Library of Medicine","doi-asserted-by":"crossref","award":["DP2-LM014268"],"award-info":[{"award-number":["DP2-LM014268"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Science Foundation","award":["2008660"],"award-info":[{"award-number":["2008660"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["J. Neural Eng."],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Machine learning (ML) models are increasingly used to generate electrical stimulation patterns in neuroprosthetic devices such as visual prostheses. While these models promise precise and personalized control, they also introduce new safety risks when model outputs are delivered directly to neural tissue. We propose a systematic, quantitative approach to detect and characterize unsafe stimulation patterns in ML-driven neurostimulation systems.\n                    <jats:italic>Approach.<\/jats:italic>\n                    We adapt an automated software testing technique known as coverage-guided fuzzing to the domain of neural stimulation. Here, fuzzing performs stress testing by perturbing model inputs and tracking whether resulting stimulation violates biophysical limits on charge density, instantaneous current, or electrode co-activation. The framework treats encoders as black boxes and steers exploration with coverage metrics that quantify how broadly test cases span the space of possible outputs and violation types.\n                    <jats:italic>Main results.<\/jats:italic>\n                    Applied to deep stimulus encoders for the retina and cortex, the method systematically reveals diverse stimulation regimes that exceed established safety limits. Two violation-output coverage metrics identify the highest number and diversity of unsafe outputs, enabling interpretable comparisons across architectures and training strategies.\n                    <jats:italic>Significance.<\/jats:italic>\n                    Violation-focused fuzzing reframes safety assessment as an empirical, reproducible process. By transforming safety from a training heuristic into a measurable property of the deployed model, it establishes a foundation for evidence-based benchmarking, regulatory readiness, and ethical assurance in next-generation neural interfaces.\n                  <\/jats:p>","DOI":"10.1088\/1741-2552\/ae4927","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T22:50:16Z","timestamp":1771887016000},"page":"026004","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Fuzzing the brain: automated stress testing for the safety of ML-driven neurostimulation"],"prefix":"10.1088","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8431-6695","authenticated-orcid":true,"given":"Mara","family":"Downing","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2945-2170","authenticated-orcid":true,"given":"Matthew","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9024-2454","authenticated-orcid":true,"given":"Jacob","family":"Granley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5233-844X","authenticated-orcid":true,"given":"Michael","family":"Beyeler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2993-1215","authenticated-orcid":false,"given":"Tevfik","family":"Bultan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,3,5]]},"reference":[{"key":"jneae4927bib1","doi-asserted-by":"publisher","first-page":"3182","DOI":"10.1109\/TSE.2023.3243522","type":"journal-article","article-title":"Black-box testing of deep neural networks through test case diversity","volume":"49","author":"Aghababaeyan","year":"2023","journal-title":"IEEE Trans. Softw. Eng."},{"key":"jneae4927bib2","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.1016\/j.clinph.2019.11.029","type":"journal-article","article-title":"An update on retinal prostheses","volume":"131","author":"Ayton","year":"2020","journal-title":"Clin. Neurophysiol."},{"key":"jneae4927bib3","doi-asserted-by":"crossref","DOI":"10.1109\/ISMAR-Adjunct68609.2025.00034","type":"preprint","article-title":"Bionic vision as neuroadaptive XR: closed-loop perceptual interfaces for neurotechnology","author":"Beyeler","year":"2025"},{"key":"jneae4927bib4","doi-asserted-by":"publisher","first-page":"9199","DOI":"10.1038\/s41598-019-45416-4","type":"journal-article","article-title":"A model of ganglion axon pathways accounts for percepts elicited by retinal implants","volume":"9","author":"Beyeler","year":"2019","journal-title":"Sci. Rep."},{"key":"jneae4927bib5","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aa795e","type":"journal-article","article-title":"Learning to see again: biological constraints on cortical plasticity and the implications for sight restoration technologies","volume":"14","author":"Beyeler","year":"2017","journal-title":"J. Neural Eng."},{"key":"jneae4927bib6","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aca69d","type":"journal-article","article-title":"Towards a Smart Bionic Eye: AI-powered artificial vision for the treatment of incurable blindness","volume":"19","author":"Beyeler","year":"2022","journal-title":"J. Neural Eng."},{"key":"jneae4927bib7","doi-asserted-by":"publisher","first-page":"254","DOI":"10.3171\/spi.2004.100.3.0254","type":"journal-article","article-title":"Safety and efficacy of spinal cord stimulation for the treatment of chronic pain: a 20-year literature review","volume":"100","author":"Cameron","year":"2004","journal-title":"J. Neurosurgery"},{"key":"jneae4927bib8","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1167\/iovs.63.11.11","type":"journal-article","article-title":"Implications of neural plasticity in retinal prosthesis","volume":"63","author":"Caravaca-Rodriguez","year":"2022","journal-title":"Investig. Ophthalmol. Visual Sci."},{"key":"jneae4927bib9","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.cose.2018.02.002","type":"journal-article","article-title":"A systematic review of fuzzing techniques","volume":"75","author":"Chen","year":"2018","journal-title":"Comput. Secur."},{"key":"jneae4927bib10","doi-asserted-by":"publisher","first-page":"1493","DOI":"10.1016\/j.visres.2009.02.003","type":"journal-article","article-title":"Simulating prosthetic vision: I. Visual models of phosphenes","volume":"49","author":"Chen","year":"2009","journal-title":"Vis. Res."},{"key":"jneae4927bib11","doi-asserted-by":"publisher","first-page":"1191","DOI":"10.1126\/science.abd7435","type":"journal-article","article-title":"Shape perception via a high-channel-count neuroprosthesis in monkey visual cortex","volume":"370","author":"Chen","year":"2020","journal-title":"Science"},{"key":"jneae4927bib12","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1167\/jov.22.2.20","type":"journal-article","article-title":"End-to-end optimization of prosthetic vision","volume":"22","author":"de Ruyter van Steveninck","year":"2022","journal-title":"J. Vision"},{"key":"jneae4927bib13","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","type":"conference-proceedings","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"jneae4927bib14","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1109\/ICECCS51672.2020.00016","type":"conference-proceedings","article-title":"An empirical study on correlation between coverage and robustness for deep neural networks","author":"Dong","year":"2020"},{"key":"jneae4927bib15","type":"dataset","article-title":"Safety Violation Fuzzing for Visual Prostheses","author":"Downing","year":"2026","unstructured":"Downing M Peng M Granley J Beyeler M Bultan T 2026 Safety Violation Fuzzing for Visual Prostheses GitHub available at : https:\/\/github.com\/mara-downing\/safety_violation_fuzzing_visual_prostheses"},{"key":"jneae4927bib16","doi-asserted-by":"publisher","first-page":"2395","DOI":"10.1109\/TASLP.2023.3282093","type":"journal-article","article-title":"A neural-network framework for the design of individualised hearing-loss compensation","volume":"31","author":"Drakopoulos","year":"2023","journal-title":"IEEE\/ACM Trans. Audio Speech Language Process."},{"key":"jneae4927bib17","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1167\/jov.25.12.12","type":"journal-article","article-title":"Perceptual learning of prosthetic vision using video game training","volume":"25","author":"Esquenazi","year":"2025","journal-title":"J. Vision"},{"key":"jneae4927bib18","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s42234-018-0013-8","type":"journal-article","article-title":"Development of visual neuroprostheses: trends and challenges","volume":"4","author":"Fernandez","year":"2018","journal-title":"Bioelectron. Med."},{"key":"jneae4927bib19","doi-asserted-by":"publisher","DOI":"10.1172\/JCI151331","type":"journal-article","article-title":"Visual percepts evoked with an intracortical 96-channel microelectrode array inserted in human occipital cortex","volume":"131","author":"Fern\u00e1ndez","year":"2021","journal-title":"J. Clin. Investig."},{"key":"jneae4927bib20","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-319-41876-6_15","type":"book","article-title":"Cortivis approach for an intracortical visual prostheses","author":"Fern\u00e1ndez","year":"2016"},{"key":"jneae4927bib21","article-title":"Improving the resolution of prosthetic vision through stimulus parameter optimization","author":"Ghaffari","year":"2021","type":"other"},{"key":"jneae4927bib22","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aba07e","type":"journal-article","article-title":"The effect of waveform asymmetry on perception with epiretinal prostheses","volume":"17","author":"Ghaffari","year":"2020","journal-title":"J. Neural Eng."},{"key":"jneae4927bib23","doi-asserted-by":"publisher","first-page":"eadv8846","DOI":"10.1126\/sciadv.adv8846","type":"journal-article","article-title":"Neural correlates of phosphene perception in blind individuals: A step toward a bidirectional cortical visual prosthesis","volume":"11","author":"Grani","year":"2025","journal-title":"Sci. Adv."},{"key":"jneae4927bib24","doi-asserted-by":"publisher","DOI":"10.3389\/fncel.2022.1034270","type":"journal-article","article-title":"Toward a personalized closed-loop stimulation of the visual cortex: Advances and challenges","volume":"16","author":"Grani","year":"2022","journal-title":"Front. Cellular Neurosci."},{"key":"jneae4927bib25","first-page":"4477","type":"conference-proceedings","article-title":"A computational model of phosphene appearance for epiretinal prostheses","author":"Granley","year":"2021"},{"key":"jneae4927bib26","article-title":"Human-in-the-loop optimization for deep stimulus encoding in visual prostheses","author":"Granley","year":"2023","type":"conference-proceedings"},{"key":"jneae4927bib27","first-page":"22671","type":"journal-article","article-title":"Hybrid neural autoencoders for stimulus encoding in visual and other sensory neuroprostheses","volume":"vol 35","author":"Granley","year":"2022a","journal-title":"Advances in Neural Information Processing Systems"},{"key":"jneae4927bib28","article-title":"Adapting brain-like neural networks for modeling cortical visual prostheses","author":"Granley","year":"2022b","type":"preprint"},{"key":"jneae4927bib29","doi-asserted-by":"publisher","first-page":"5017","DOI":"10.1167\/iovs.08-2897","type":"journal-article","article-title":"Brightness as a function of current amplitude in human retinal electrical stimulation","volume":"50","author":"Greenwald","year":"2009","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"jneae4927bib30","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1109\/51.395310","type":"journal-article","article-title":"Stimulus waveforms for selective neural stimulation","volume":"14","author":"Grill","year":"1995","journal-title":"IEEE Eng. Med. Biol. Mag."},{"key":"jneae4927bib31","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1167\/iovs.10-5282","type":"journal-article","article-title":"Temporal interactions during paired-electrode stimulation in two retinal prosthesis subjects","volume":"52","author":"Horsager","year":"2011","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"jneae4927bib32","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1167\/iovs.08-2595","type":"journal-article","article-title":"Predicting visual sensitivity in retinal prosthesis patients","volume":"50","author":"Horsager","year":"2009","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"jneae4927bib33","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ad31c4","type":"journal-article","article-title":"Axonal stimulation affects the linear summation of single-point perception in three Argus II users","volume":"21","author":"Hou","year":"2024","journal-title":"J. Neural Eng."},{"key":"jneae4927bib34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3688835","type":"journal-article","article-title":"Neuron semantic-guided test generation for deep neural networks fuzzing","volume":"34","author":"Huang","year":"2024","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"jneae4927bib35","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ade918","type":"journal-article","article-title":"End-to-end learning of safe stimulation parameters for cortical neuroprosthetic vision","volume":"22","author":"K\u00fc\u00e7\u00fcko\u011flu","year":"2025","journal-title":"J. Neural Eng."},{"key":"jneae4927bib36","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1109\/icse-nier.2019.00031","type":"conference-proceedings","article-title":"Structural coverage criteria for neural networks could be misleading","author":"Li","year":"2019"},{"key":"jneae4927bib37","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1002\/ana.23951","type":"journal-article","article-title":"Adaptive deep brain stimulation in advanced Parkinson disease","volume":"74","author":"Little","year":"2013","journal-title":"Ann. Neurol."},{"key":"jneae4927bib38","doi-asserted-by":"publisher","first-page":"2753","DOI":"10.1167\/iovs.18-25750","type":"journal-article","article-title":"Visual Cortical Plasticity in Retinitis Pigmentosa","volume":"60","author":"Lunghi","year":"2019","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"jneae4927bib39","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1145\/3238147.3238202","type":"conference-proceedings","article-title":"Deepgauge: Multi-granularity testing criteria for deep learning systems","author":"Ma","year":"2018"},{"key":"jneae4927bib40","doi-asserted-by":"publisher","first-page":"996","DOI":"10.1109\/10.102812","type":"journal-article","article-title":"Charge density and charge per phase as cofactors in neural injury induced by electrical stimulation","volume":"37","author":"McCreery","year":"1990","journal-title":"IEEE Trans. Bio-Med. Eng."},{"key":"jneae4927bib41","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.jneumeth.2004.10.020","type":"journal-article","article-title":"Electrical stimulation of excitable tissue: design of efficacious and safe protocols","volume":"141","author":"Merrill","year":"2005","journal-title":"J. Neurosci. Methods"},{"key":"jneae4927bib42","doi-asserted-by":"publisher","DOI":"10.1101\/2025.09.24.678361v1)","type":"other","article-title":"Deep learning-based control of electrically evoked activity in human visual cortex","author":"Moure","year":"2025"},{"key":"jneae4927bib43","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1167\/tvst.13.11.28","type":"journal-article","article-title":"Aligning Visual Prosthetic Development With Implantee Needs","volume":"13","author":"Nadolskis","year":"2024","journal-title":"Transl. Vis. Sci. Technol."},{"key":"jneae4927bib44","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1167\/iovs.11-8401","type":"journal-article","article-title":"Frequency and amplitude modulation have different effects on the percepts elicited by retinal stimulation","volume":"53","author":"Nanduri","year":"2012","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"jneae4927bib45","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/6\/3\/035001","type":"journal-article","article-title":"Toward the development of a cortically based visual neuroprosthesis","volume":"6","author":"Normann","year":"2009","journal-title":"J. Neural Eng."},{"key":"jneae4927bib46","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aae398","type":"journal-article","article-title":"Biomimetic encoding model for restoring touch in bionic hands through a nerve interface","volume":"15","author":"Okorokova","year":"2018","journal-title":"J. Neural Eng."},{"key":"jneae4927bib47","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1148\/radiol.2017171920","type":"journal-article","article-title":"Methodologic guide for evaluating clinical performance and effect of artificial intelligence technology for medical diagnosis and prediction","volume":"286","author":"Park","year":"2018","journal-title":"Radiology"},{"key":"jneae4927bib48","first-page":"1","type":"conference-proceedings","article-title":"Deepxplore: automated whitebox testing of deep learning systems","author":"Pei","year":"2017"},{"key":"jneae4927bib49","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.conb.2019.03.008","type":"journal-article","article-title":"Towards Neural Co-Processors for the Brain: Combining decoding and encoding in brain-computer interfaces","volume":"55","author":"Rao","year":"2019","journal-title":"Curr. Opin. Neurobiol."},{"key":"jneae4927bib50","doi-asserted-by":"crossref","DOI":"10.1109\/EMBC58623.2025.11253762","type":"preprint","article-title":"Evaluating deep human-in-the-loop optimization for retinal implants using sighted participants","author":"Schoinas","year":"2025"},{"key":"jneae4927bib51","author":"Second Sight","year":"2013","type":"book"},{"key":"jneae4927bib52","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aba8b1","type":"journal-article","article-title":"Computational challenges and opportunities for a bi-directional artificial retina","volume":"17","author":"Shah","year":"2020","journal-title":"J. Neural Eng."},{"key":"jneae4927bib53","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13825","type":"journal-article","article-title":"Rapid control and feedback rates enhance neuroprosthetic control","volume":"8","author":"Shanechi","year":"2017","journal-title":"Nat. Commun."},{"key":"jneae4927bib54","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1109\/10.126616","type":"journal-article","article-title":"A model of safe levels for electrical stimulation","volume":"39","author":"Shannon","year":"1992","journal-title":"IEEE Trans. Bio-Med. Eng."},{"key":"jneae4927bib55","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1016\/j.neuron.2014.08.038","type":"journal-article","article-title":"Combining decoder design and neural adaptation in brain-machine interfaces","volume":"84","author":"Shenoy","year":"2014","journal-title":"Neuron"},{"key":"jneae4927bib56","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","type":"preprint"},{"key":"jneae4927bib57","article-title":"Humanitarian device exemption h110002 supplement s017","author":"U.S. Food and Drug Administration","type":"journal-article"},{"key":"jneae4927bib58","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.85812","type":"journal-article","article-title":"Towards biologically plausible phosphene simulation for the differentiable optimization of visual cortical prostheses","volume":"13","author":"van der Grinten","year":"2024","journal-title":"eLife"},{"key":"jneae4927bib59","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/8\/4\/046016","type":"journal-article","article-title":"Electric crosstalk impairs spatial resolution of multi-electrode arrays in retinal implants","volume":"8","author":"Wilke","year":"2011","journal-title":"J. Neural Eng."},{"key":"jneae4927bib60","doi-asserted-by":"publisher","DOI":"10.1101\/2025.04.25.650658","type":"other","article-title":"Optimizing electrode placement and information capacity for local field potentials in cortex","author":"Willis","year":"2025"},{"key":"jneae4927bib61","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1145\/3293882.3330579","type":"conference-proceedings","article-title":"Deephunter: a coverage-guided fuzz testing framework for deep neural networks","author":"Xie","year":"2019"},{"key":"jneae4927bib62","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1109\/saner53432.2022.00056","type":"conference-proceedings","article-title":"Revisiting neuron coverage metrics and quality of deep neural networks","author":"Yang","year":"2022"},{"key":"jneae4927bib63","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.901337","type":"journal-article","article-title":"Factors affecting two-point discrimination in Argus II patients","volume":"16","author":"Y\u00fccel","year":"2022","journal-title":"Front. Neurosci."},{"key":"jneae4927bib64","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1038\/551159a","type":"journal-article","article-title":"Four ethical priorities for neurotechnologies and AI","volume":"551","author":"Yuste","year":"2017","journal-title":"Nature"}],"container-title":["Journal of Neural Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae4927","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae4927\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae4927","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae4927\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae4927\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae4927\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae4927\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae4927\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T10:50:50Z","timestamp":1772707850000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ae4927"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,5]]},"references-count":64,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,3,5]]},"published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1741-2552\/ae4927","relation":{},"ISSN":["1741-2560","1741-2552"],"issn-type":[{"value":"1741-2560","type":"print"},{"value":"1741-2552","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,5]]},"assertion":[{"value":"Fuzzing the brain: automated stress testing for the safety of ML-driven neurostimulation","name":"article_title","label":"Article Title"},{"value":"Journal of Neural Engineering","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-11-24","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-02-23","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-03-05","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}