{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:39:22Z","timestamp":1773171562069,"version":"3.50.1"},"reference-count":98,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T00:00:00Z","timestamp":1658361600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T00:00:00Z","timestamp":1658361600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"DOE Office of Science, Office of High Energy Physics","award":["DE-AC02-07CH11359"],"award-info":[{"award-number":["DE-AC02-07CH11359"]}]},{"name":"DOE Office of Science, Office of Advanced Scientific Computing Research, applied mathematics and SciDAC programs","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2022,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>With increased adoption of supervised deep learning methods for work with cosmological survey data, the assessment of data perturbation effects (that can naturally occur in the data processing and analysis pipelines) and the development of methods that increase model robustness are increasingly important. In the context of morphological classification of galaxies, we study the effects of perturbations in imaging data. In particular, we examine the consequences of using neural networks when training on baseline data and testing on perturbed data. We consider perturbations associated with two primary sources: (a) increased observational noise as represented by higher levels of Poisson noise and (b) data processing noise incurred by steps such as image compression or telescope errors as represented by one-pixel adversarial attacks. We also test the efficacy of <jats:italic>domain adaptation<\/jats:italic> techniques in mitigating the perturbation-driven errors. We use classification accuracy, latent space visualizations, and latent space distance to assess model robustness in the face of these perturbations. For deep learning models without domain adaptation, we find that processing pixel-level errors easily flip the classification into an incorrect class and that higher observational noise makes the model trained on low-noise data unable to classify galaxy morphologies. On the other hand, we show that training with domain adaptation improves model robustness and mitigates the effects of these perturbations, improving the classification accuracy up to 23% on data with higher observational noise. Domain adaptation also increases up to a factor of <jats:inline-formula>\n                     <jats:tex-math\/>\n                     <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                           <mml:mo>\u2248<\/mml:mo>\n                        <\/mml:mrow>\n                        <mml:mn>2.3<\/mml:mn>\n                     <\/mml:math>\n                     <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"mlstac7f1aieqn1.gif\" xlink:type=\"simple\"\/>\n                  <\/jats:inline-formula> the latent space distance between the baseline and the incorrectly classified one-pixel perturbed image, making the model more robust to inadvertent perturbations. Successful development and implementation of methods that increase model robustness in astronomical survey pipelines will help pave the way for many more uses of deep learning for astronomy.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac7f1a","type":"journal-article","created":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T22:44:06Z","timestamp":1657147446000},"page":"035007","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["DeepAdversaries: examining the robustness of deep learning models for galaxy morphology classification"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1281-7192","authenticated-orcid":true,"given":"Aleksandra","family":"\u0106iprijanovi\u0107","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1716-463X","authenticated-orcid":false,"given":"Diana","family":"Kafkes","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4226-304X","authenticated-orcid":false,"given":"Gregory","family":"Snyder","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3136-9532","authenticated-orcid":false,"given":"F Javier","family":"S\u00e1nchez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6785-8720","authenticated-orcid":true,"given":"Gabriel Nathan","family":"Perdue","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2260-9151","authenticated-orcid":false,"given":"Kevin","family":"Pedro","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6706-8972","authenticated-orcid":false,"given":"Brian","family":"Nord","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0437-8655","authenticated-orcid":true,"given":"Sandeep","family":"Madireddy","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6099-2772","authenticated-orcid":true,"given":"Stefan M","family":"Wild","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2022,7,21]]},"reference":[{"key":"mlstac7f1abib1","article-title":"Robustness to adversarial examples through an ensemble of specialists","author":"Abbasi","year":"2017"},{"key":"mlstac7f1abib2","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1093\/mnras\/stw641","article-title":"The Dark Energy Survey: more than dark energy\u2014an overview","volume":"460","author":"Abbott","year":"2016","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib3","article-title":"The DESI experiment part I: science,targeting, and survey design","author":"Aghamousa","year":"2016a"},{"key":"mlstac7f1abib4","article-title":"The DESI experiment part II: instrument design","author":"Aghamousa","year":"2016b"},{"key":"mlstac7f1abib5","doi-asserted-by":"publisher","first-page":"S4","DOI":"10.1093\/pasj\/psx066","article-title":"The hyper suprime-cam SSP survey: overview and survey design","volume":"70","author":"Aihara","year":"2018","journal-title":"Publ. Astron. Soc. Japan"},{"key":"mlstac7f1abib6","article-title":"Sky surveys scheduling using reinforcement learning","author":"Alba Hernandez","year":"2019"},{"key":"mlstac7f1abib7","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.105.084054","article-title":"Using supervised learning algorithms as a follow-up method in the search of gravitational waves from core-collapse supernovae","volume":"105","author":"Antelis","year":"2022","journal-title":"Phys. Rev. D"},{"key":"mlstac7f1abib8","author":"Borg","year":"2005"},{"key":"mlstac7f1abib9","article-title":"Adversarial examples, uncertainty, and transfer testing robustness in Gaussian process hybrid deep networks","author":"Bradshaw","year":"2017"},{"key":"mlstac7f1abib10","doi-asserted-by":"crossref","DOI":"10.1145\/3128572.3140448","article-title":"ZOO: zeroth order optimization based black-box attacks to deep neural networks without training substitute models","author":"Chen","year":"2017"},{"key":"mlstac7f1abib11","author":"\u0106iprijanovi\u0107","year":"2021"},{"key":"mlstac7f1abib12","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1093\/mnras\/stab1677","article-title":"DeepMerge\u2014II. Building robust deep learning algorithms for merging galaxy identification across domains","volume":"506","author":"\u0106iprijanovi\u0107","year":"2021a","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib13","article-title":"Domain adaptation techniques for improved cross-domain study of galaxy mergers","author":"\u0106iprijanovi\u0107","year":"2020a"},{"key":"mlstac7f1abib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ascom.2020.100390","article-title":"DeepMerge: classifying high-redshift merging galaxies with deep neural networks","volume":"32","author":"\u0106iprijanovi\u0107","year":"2020b","journal-title":"Astron. Comput."},{"key":"mlstac7f1abib15","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.5514180","article-title":"DeepAdversaries: Examining the Robustness of Deep Learning Models for Galaxy Morphology Classification (Data)","author":"\u0106iprijanovi\u0107","year":"2021b"},{"key":"mlstac7f1abib16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.101.102003","article-title":"Efficient gravitational-wave glitch identification from environmental data through machine learning","volume":"101","author":"Colgan","year":"2020","journal-title":"Phys. Rev. D"},{"key":"mlstac7f1abib17","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1086\/377318","article-title":"A direct measurement of major galaxy mergers at z\u22723","volume":"126","author":"Conselice","year":"2003","journal-title":"Astrophys. J."},{"key":"mlstac7f1abib18","first-page":"1","author":"Csurka","year":"2017"},{"key":"mlstac7f1abib19","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1111\/j.1365-2966.2009.15686.x","article-title":"Galaxy zoo: the fraction of merging galaxies in the SDSS and their morphologies","volume":"401","author":"Darg","year":"2010","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib20","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TEVC.2010.2059031","article-title":"Differential evolution: a survey of the state-of-the-art","volume":"15","author":"Das","year":"2011","journal-title":"IEEE Trans. Evol. Comput."},{"key":"mlstac7f1abib21","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"mlstac7f1abib22","first-page":"2464","article-title":"Interpreting robust optimization via adversarial influence functions","author":"Deng","year":"2020"},{"key":"mlstac7f1abib23","doi-asserted-by":"crossref","DOI":"10.1109\/QoMEX.2016.7498955","article-title":"Understanding how image quality affects deep neural networks","author":"Dodge","year":"2016"},{"key":"mlstac7f1abib24","doi-asserted-by":"crossref","DOI":"10.1109\/ICCCN.2017.8038465","article-title":"A study and comparison of human and deep learning recognition performance under visual distortions","author":"Dodge","year":"2017"},{"key":"mlstac7f1abib25","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1093\/mnras\/sty3497","article-title":"Transfer learning for galaxy morphology from one survey to another","volume":"484","author":"Dom\u00ednguez S\u00e1nchez","year":"2019","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib26","article-title":"Robust physical-world attacks on deep learning models","author":"Eykholt","year":"2017"},{"key":"mlstac7f1abib27","article-title":"Detecting adversarial samples from artifacts","author":"Feinman","year":"2017"},{"key":"mlstac7f1abib28","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.100.063514","article-title":"Cosmological constraints with deep learning from KiDS-450 weak lensing maps","volume":"100","author":"Fluri","year":"2019","journal-title":"Phys. Rev. D"},{"key":"mlstac7f1abib29","article-title":"Adversarial examples are a natural consequence of test error in noise","author":"Ford","year":"2019"},{"key":"mlstac7f1abib30","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"mlstac7f1abib31","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.physletb.2017.12.053","article-title":"Deep learning for real-time gravitational wave detection and parameter estimation: results with advanced LIGO data","volume":"778","author":"George","year":"2018","journal-title":"Phys. Lett. B"},{"key":"mlstac7f1abib32","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1093\/mnras\/stab3044","article-title":"Convolutional deep denoising autoencoders for radio astronomical images","volume":"509","author":"Gheller","year":"2022","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib33","article-title":"The effect of distortions on the prediction of visual attention","author":"Gide","year":"2016"},{"key":"mlstac7f1abib34","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1080\/01621459.1962.10500553","article-title":"Variance formulas for the mean difference and coefficient of concentration","volume":"57","author":"Glasser","year":"1962","journal-title":"J. Am. Stat. Assoc."},{"key":"mlstac7f1abib35","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"mlstac7f1abib36","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"mlstac7f1abib37","first-page":"513","article-title":"A kernel method for the two-sample-problem","volume":"vol 19","author":"Gretton","year":"2007"},{"key":"mlstac7f1abib38","article-title":"Towards deep neural network architectures robust to adversarial examples","author":"Gu","year":"2014"},{"key":"mlstac7f1abib39","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"mlstac7f1abib40","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"mlstac7f1abib41","article-title":"Adversarial examples are not bugs, they are features","volume":"vol 32","author":"Ilyas","year":"2019"},{"key":"mlstac7f1abib42","doi-asserted-by":"publisher","first-page":"111","DOI":"10.3847\/1538-4357\/ab042c","article-title":"LSST: from science drivers to reference design and anticipated data products","volume":"873","author":"Ivezi\u0107","year":"2019","journal-title":"Astrophys. J."},{"key":"mlstac7f1abib43","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00503","article-title":"Contrastive adaptation network for unsupervised domain adaptation","author":"Kang","year":"2019"},{"key":"mlstac7f1abib44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-63387-9_5","article-title":"Reluplex: an efficient SMT solver for verifying deep neural networks","author":"Katz","year":"2017"},{"key":"mlstac7f1abib45","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"mlstac7f1abib46","author":"Krizhevsky","year":"2009"},{"key":"mlstac7f1abib47","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"mlstac7f1abib48","doi-asserted-by":"publisher","DOI":"10.1016\/j.ascom.2021.100489","article-title":"A real time processing system for big data in astronomy: applications to HERA","volume":"36","author":"La Plante","year":"2021","journal-title":"Astron. Comput."},{"key":"mlstac7f1abib49","doi-asserted-by":"publisher","first-page":"3895","DOI":"10.1093\/mnras\/stx1665","article-title":"CMU DeepLens: deep learning for automatic image-based galaxy-galaxy strong lens finding","volume":"473","author":"Lanusse","year":"2018","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib50","first-page":"5874","article-title":"Implicit Euler skip connections: enhancing adversarial robustness via numerical stability","author":"Li","year":"2020"},{"key":"mlstac7f1abib51","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/18.61115","article-title":"Divergence measures based on the shannon entropy","volume":"37","author":"Lin","year":"1991","journal-title":"IEEE Trans. Inf. Theory"},{"key":"mlstac7f1abib52","doi-asserted-by":"publisher","first-page":"4149","DOI":"10.1093\/mnras\/stab2229","article-title":"DeepSZ: identification of Sunyaev\u2013Zel\u2019dovich galaxy clusters using deep learning","volume":"507","author":"Lin","year":"2021","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib53","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1111\/j.1365-2966.2008.13689.x","article-title":"Galaxy Zoo: morphologies derived from visual inspection of galaxies from the Sloan digital sky survey","volume":"389","author":"Lintott","year":"2008","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib54","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1111\/j.1365-2966.2010.17432.x","article-title":"Galaxy Zoo 1: data release of morphological classifications for nearly 900\u2009000 galaxies","volume":"410","author":"Lintott","year":"2010","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib55","article-title":"Conditional adversarial domain adaptation","author":"Long","year":"2017"},{"key":"mlstac7f1abib56","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1086\/421849","article-title":"A new nonparametric approach to galaxy morphological classification","volume":"128","author":"Lotz","year":"2004","journal-title":"Astrophys. J."},{"key":"mlstac7f1abib57","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1109\/ICCV.2017.56","article-title":"SafetyNet: detecting and rejecting adversarial examples robustly","author":"Lu","year":"2017"},{"key":"mlstac7f1abib58","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2018"},{"key":"mlstac7f1abib59","doi-asserted-by":"publisher","first-page":"5113","DOI":"10.1093\/mnras\/sty2206","article-title":"First results from the IllustrisTNG simulations: radio haloes and magnetic fields","volume":"480","author":"Marinacci","year":"2018","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib60","article-title":"On detecting adversarial perturbations","author":"Metzen","year":"2017"},{"key":"mlstac7f1abib61","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.105.083018","article-title":"Search for binary black hole mergers in the third observing run of Advanced LIGO-Virgo using coherent WaveBurst enhanced with machine learning","volume":"105","author":"Mishra","year":"2022","journal-title":"Phys. Rev. D"},{"key":"mlstac7f1abib62","doi-asserted-by":"publisher","first-page":"151","DOI":"10.3847\/1538-3881","article-title":"A framework for telescope schedulers: with applications to the large synoptic survey telescope","volume":"157","author":"Naghib","year":"2019","journal-title":"Astrophys. J."},{"key":"mlstac7f1abib63","doi-asserted-by":"publisher","first-page":"1206","DOI":"10.1093\/mnras\/sty618","article-title":"First results from the IllustrisTNG simulations: a tale of two elements\u2014chemical evolution of magnesium and europium","volume":"477","author":"Naiman","year":"2018","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib64","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s40668-019-0028-x","article-title":"The IllustrisTNG simulations: public data release","volume":"6","author":"Nelson","year":"2019","journal-title":"Comput. Astrophys. Cosmol."},{"key":"mlstac7f1abib65","article-title":"Exploring the space of black-box attacks on deep neural networks","author":"Nitin Bhagoji","year":"2017"},{"key":"mlstac7f1abib66","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1109\/SP.2016.41","article-title":"Distillation as a defense to adversarial perturbations against deep neural networks","author":"Papernot","year":"2016"},{"key":"mlstac7f1abib67","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1080\/14786440109462720","article-title":"LIII. On lines and planes of closest fit to systems of points in space","volume":"2","author":"Pearson","year":"1901","journal-title":"London, Edinburgh Dublin Phil. Mag. J. Sci."},{"key":"mlstac7f1abib68","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"mlstac7f1abib69","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1093\/mnras\/stx3112","article-title":"First results from the IllustrisTNG simulations: the stellar mass content of groups and clusters of galaxies","volume":"475","author":"Pillepich","year":"2018","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib70","doi-asserted-by":"publisher","first-page":"3852","DOI":"10.1093\/mnras\/stab3215","article-title":"Machine learning astrophysics from 21 cm lightcones: impact of network architectures and signal contamination","volume":"509","author":"Prelogovi\u0107","year":"2022","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib71","doi-asserted-by":"publisher","first-page":"4140","DOI":"10.1093\/mnras\/sty3345","article-title":"The optical morphologies of galaxies in the IllustrisTNG simulation: a comparison to Pan-STARRS observations","volume":"483","author":"Rodriguez-Gomez","year":"2019","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib72","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.ascom.2015.02.002","article-title":"GALSIM: the modular galaxy image simulation toolkit","volume":"10","author":"Rowe","year":"2015","journal-title":"Astron. Comput."},{"key":"mlstac7f1abib73","doi-asserted-by":"publisher","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","article-title":"Nonlinear dimensionality reduction by locally linear embedding","volume":"290","author":"Roweis","year":"2000","journal-title":"Science"},{"key":"mlstac7f1abib74","article-title":"Universal domain adaptation through self supervision","author":"Saito","year":"2020"},{"key":"mlstac7f1abib75","doi-asserted-by":"publisher","first-page":"043","DOI":"10.1088\/1475-7516\/2021\/07\/043","article-title":"Effects of overlapping sources on cosmic shear estimation: Statistical sensitivity and pixel-noise bias","volume":"2021","author":"Sanchez","year":"2021","journal-title":"J. Cosmol. Astropart. Phys."},{"key":"mlstac7f1abib76","first-page":"41","article-title":"Influence of the atmospheric and instrumental dispersion on the brightness distribution in a galaxy","volume":"6","author":"S\u00e9rsic","year":"1963","journal-title":"Bol. Asoc. Argentina Astron."},{"key":"mlstac7f1abib77","first-page":"13","author":"Smola","year":"2007"},{"key":"mlstac7f1abib78","doi-asserted-by":"publisher","first-page":"1886","DOI":"10.1093\/mnras\/stv2078","article-title":"Galaxy morphology and star formation in the illustris simulation at z\u2009=\u20090","volume":"454","author":"Snyder","year":"2015","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib79","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1093\/mnras\/stx3304","article-title":"First results from the IllustrisTNG simulations: matter and galaxy clustering","volume":"475","author":"Springel","year":"2018","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib80","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1023\/A:1008202821328","article-title":"Differential evolution\u2014a simple and efficient heuristic for global optimization over continuous spaces","volume":"11","author":"Storn","year":"1997","journal-title":"J. Glob. Optim."},{"key":"mlstac7f1abib81","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1109\/TEVC.2019.2890858","article-title":"One pixel attack for fooling deep neural networks","volume":"23","author":"Su","year":"2019","journal-title":"IEEE Trans. Evol. Comput."},{"key":"mlstac7f1abib82","article-title":"One pixel attack for fooling deep neural networks","author":"Su","year":"2017"},{"key":"mlstac7f1abib83","doi-asserted-by":"publisher","DOI":"10.1117\/1.JATIS.1.3.035001","article-title":"Prime focus spectrograph for the Subaru telescope: massively multiplexed optical and near-infrared fiber spectrograph","volume":"1","author":"Sugai","year":"2015","journal-title":"J. Astron. Telesc. Instrum. Syst."},{"key":"mlstac7f1abib84","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-49409-8_35","article-title":"Deep CORAL: Correlation alignment for deep domain adaptation","author":"Sun","year":"2016"},{"key":"mlstac7f1abib85","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013"},{"key":"mlstac7f1abib86","article-title":"DeepGhostBusters: using mask R-CNN to detect and mask ghosting and scattered-light artifacts from optical survey images","author":"Tanoglidis","year":"2021b"},{"key":"mlstac7f1abib87","doi-asserted-by":"publisher","DOI":"10.1016\/j.ascom.2021.100469","article-title":"DeepShadows: separating low surface brightness galaxies from artifacts using deep learning","volume":"35","author":"Tanoglidis","year":"2021a","journal-title":"Astron. Comput."},{"key":"mlstac7f1abib88","doi-asserted-by":"publisher","first-page":"2319","DOI":"10.1126\/science.290.5500.2319","article-title":"A global geometric framework for nonlinear dimensionality reduction","volume":"290","author":"Tenenbaum","year":"2000","journal-title":"Science"},{"key":"mlstac7f1abib89","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1093\/mnras\/stx3186","article-title":"Deep learning for galaxy surface brightness profile fitting","volume":"475","author":"Tuccillo","year":"2018","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib90","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"mlstac7f1abib91","doi-asserted-by":"publisher","first-page":"1518","DOI":"10.1093\/mnras\/stu1536","article-title":"Introducing the illustris project: simulating the coevolution of dark and visible matter in the universe","volume":"444","author":"Vogelsberger","year":"2014","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac7f1abib92","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.neucom.2018.05.083","article-title":"Deep visual domain adaptation: a survey","volume":"312","author":"Wang","year":"2018","journal-title":"Neurocomputing"},{"key":"mlstac7f1abib93","first-page":"311","author":"Warde-Farley","year":"2017"},{"key":"mlstac7f1abib94","first-page":"2431","article-title":"Bayesian inference with certifiable adversarial robustness","volume":"vol 130","author":"Wicker","year":"2021"},{"key":"mlstac7f1abib95","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3400066","article-title":"A survey of unsupervised deep domain adaptation","volume":"11","author":"Wilson","year":"2020","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"mlstac7f1abib96","doi-asserted-by":"publisher","first-page":"2805","DOI":"10.1109\/TNNLS.2018.2886017","article-title":"Adversarial examples: attacks and defenses for deep learning","volume":"30","author":"Yuan","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"mlstac7f1abib97","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.ins.2019.01.02","article-title":"Robust unsupervised domain adaptation for neural networks via moment alignment","volume":"483","author":"Zellinger","year":"2019","journal-title":"Inf. Sci."},{"key":"mlstac7f1abib98","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1137\/1.9781611976236.53","article-title":"Fisher deep domain adaptation","author":"Zhang","year":"2020"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac7f1a","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac7f1a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac7f1a","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac7f1a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac7f1a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac7f1a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac7f1a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac7f1a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T09:34:34Z","timestamp":1658396074000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac7f1a"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,21]]},"references-count":98,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,7,21]]},"published-print":{"date-parts":[[2022,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac7f1a","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,21]]},"assertion":[{"value":"DeepAdversaries: examining the robustness of deep learning models for galaxy morphology classification","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-04-29","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-07-06","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-07-21","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}