{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T08:02:42Z","timestamp":1780300962709,"version":"3.54.0"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:00:00Z","timestamp":1778112000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Science of Computer Programming"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.scico.2026.103502","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:20:26Z","timestamp":1778084426000},"page":"103502","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["GIFTbench: Generative image fuzz testing benchmark"],"prefix":"10.1016","volume":"253","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4815-6253","authenticated-orcid":false,"given":"Maryam","family":"Maryam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7825-3409","authenticated-orcid":false,"given":"Matteo","family":"Biagiola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8956-3894","authenticated-orcid":false,"given":"Andrea","family":"Stocco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6229-8231","authenticated-orcid":false,"given":"Vincenzo","family":"Riccio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.scico.2026.103502_bib0001","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1016\/j.procs.2021.01.025","article-title":"Deep learning in image classification using residual network (resnet) variants for detection of colorectal cancer","volume":"179","author":"Sarwinda","year":"2021","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.scico.2026.103502_bib0002","series-title":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","first-page":"31","article-title":"Testing of autonomous driving systems: where are we and where should we go?","author":"Lou","year":"2022"},{"key":"10.1016\/j.scico.2026.103502_bib0003","unstructured":"S. Tang, Z. Zhang, Y. Zhang, J. Zhou, Y. Guo, S. Liu, S. Guo, Y.-F. Li, L. Ma, Y. Xue, Y. Liu, A survey on automated driving system testing: landscapes and trends, 2023. 2206.05961."},{"key":"10.1016\/j.scico.2026.103502_bib0004","series-title":"Proceedings of the 43rd International Conference on Software Engineering, ICSE \u201921","first-page":"348","article-title":"Operation is the hardest teacher: estimating DNN accuracy looking for mispredictions","author":"Guerriero","year":"2021"},{"key":"10.1016\/j.scico.2026.103502_bib0005","series-title":"Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis","first-page":"954","article-title":"Deepatash: focused test generation for deep learning systems","author":"Zohdinasab","year":"2023"},{"issue":"1","key":"10.1016\/j.scico.2026.103502_bib0006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TSE.2019.2962027","article-title":"Machine learning testing: survey, landscapes and horizons","volume":"48","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Software Eng."},{"issue":"6","key":"10.1016\/j.scico.2026.103502_bib0007","doi-asserted-by":"crossref","first-page":"5193","DOI":"10.1007\/s10664-020-09881-0","article-title":"Testing machine learning based systems: a systematic mapping","volume":"25","author":"Riccio","year":"2020","journal-title":"Empir. Software Eng."},{"key":"10.1016\/j.scico.2026.103502_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2020.110542","article-title":"On testing machine learning programs","volume":"164","author":"Braiek","year":"2020","journal-title":"J. Syst. Software"},{"key":"10.1016\/j.scico.2026.103502_bib0009","series-title":"2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE)","first-page":"1161","article-title":"When and why test generators for deep learning produce invalid inputs: an empirical study","author":"Riccio","year":"2023"},{"key":"10.1016\/j.scico.2026.103502_bib0010","series-title":"2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE)","first-page":"226","article-title":"Distribution-aware testing of neural networks using generative models","author":"Dola","year":"2021"},{"key":"10.1016\/j.scico.2026.103502_bib0011","series-title":"Proceedings of the IEEE\/ACM 42nd International Conference on Software Engineering Workshops","first-page":"521","article-title":"Search-based image space navigation for dnn image classifier test input generation","author":"Kang","year":"2020"},{"key":"10.1016\/j.scico.2026.103502_bib0012","series-title":"Proceedings of the 30th ACM SIGSOFT International Symposium on Software Testing and Analysis","first-page":"56","article-title":"Exposing previously undetectable faults in deep neural networks","author":"Dunn","year":"2021"},{"key":"10.1016\/j.scico.2026.103502_bib0013","series-title":"2023 IEEE\/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE)","article-title":"Software testing of generative ai systems: challenges and opportunities","author":"Aleti","year":"2023"},{"key":"10.1016\/j.scico.2026.103502_bib0014","series-title":"Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering","first-page":"1","article-title":"Cit4dnn: generating diverse and rare inputs for neural networks using latent space combinatorial testing","author":"Dola","year":"2024"},{"key":"10.1016\/j.scico.2026.103502_bib0015","article-title":"Targeted deep learning system boundary testing","author":"l","year":"2025","journal-title":"ACM Trans. Software Eng. Methodol."},{"key":"10.1016\/j.scico.2026.103502_bib0016","series-title":"Proceedings of 47th International Conference on Software Engineering, ICSE \u201925","article-title":"Efficient domain augmentation for autonomous driving testing using diffusion models","author":"Baresi","year":"2025"},{"key":"10.1016\/j.scico.2026.103502_bib0017","series-title":"2025 IEEE Conference on Software Testing, Verification and Validation (ICST)","first-page":"174","article-title":"Benchmarking generative AI models for deep learning test input generation","author":"Maryam","year":"2025"},{"issue":"11","key":"10.1016\/j.scico.2026.103502_bib0018","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"10.1016\/j.scico.2026.103502_bib0019","series-title":"2025 IEEE Conference on Software Testing, Verification and Validation (ICST)","first-page":"801","article-title":"ICST tool competition 2025-self-driving car testing track","author":"Birchler","year":"2025"},{"key":"10.1016\/j.scico.2026.103502_bib0020","series-title":"2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC)","first-page":"1095","article-title":"Enhancing valid test input generation with distribution awareness for deep neural networks","author":"Zhang","year":"2024"},{"key":"10.1016\/j.scico.2026.103502_bib0021","series-title":"IEEE\/ACM International Workshop on Search-Based and Fuzz Testing","first-page":"45","article-title":"Sbft tool competition 2023-cyber-physical systems track","author":"Biagiola","year":"2023"},{"key":"10.1016\/j.scico.2026.103502_bib0022","series-title":"2025 IEEE Conference on Software Testing, Verification and Validation (ICST)","first-page":"150","article-title":"Benchmarking image perturbations for testing automated driving assistance systems","author":"Lambertenghi","year":"2025"},{"key":"10.1016\/j.scico.2026.103502_bib0023","unstructured":"A. Abid, A. Abdalla, A. Abid, D. Khan, A. Alfozan, J. Zou, Gradio: hassle-free sharing and testing of ML models in the wild, 2019. 1906.02569."},{"key":"10.1016\/j.scico.2026.103502_bib0024","series-title":"GIFTbench web-based application: Release v1.2.0","article-title":"Giftbench","author":"Maryam","year":"2025"},{"key":"10.1016\/j.scico.2026.103502_bib0025","unstructured":"D.P. Kingma, M. Welling, Auto-encoding variational bayes(2022). 1312.6114."},{"key":"10.1016\/j.scico.2026.103502_bib0026","unstructured":"J. Sohl-Dickstein, E.A. Weiss, N. Maheswaranathan, S. Ganguli, Deep unsupervised learning using nonequilibrium thermodynamics (2015). 1503.03585."},{"key":"10.1016\/j.scico.2026.103502_bib0027","unstructured":"Gradio, Gradio: build machine learning demos in python, 2025, https:\/\/www.gradio.app. Accessed: 2025-05-30."},{"issue":"6","key":"10.1016\/j.scico.2026.103502_bib0028","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The mnist database of handwritten digit images for machine learning research","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"10.1016\/j.scico.2026.103502_bib0029","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.scico.2026.103502_bib0030","unstructured":"PyTorch Team, TorchScript: a way to create serializable and optimized models from pytorch code, 2018, https:\/\/pytorch.org\/docs\/stable\/jit.html. Accessed: 2025-05-30."},{"key":"10.1016\/j.scico.2026.103502_bib0031","unstructured":"M. Maryam, M. Biagiola, A. Stocco, V. Riccio, GIFTbench user guide, 2025, https:\/\/deeptestai.github.io\/genai_tigs\/user-guide\/. accessed: 2026-04-04."},{"key":"10.1016\/j.scico.2026.103502_bib0032","unstructured":"PyTorch Contributors, Source code for torchvision.models.VGG, 2024, https:\/\/pytorch.org\/vision\/0.12\/_modules\/torchvision\/models\/vgg.html#vgg19. Accessed: 2024-01-01."},{"issue":"4","key":"10.1016\/j.scico.2026.103502_bib0033","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1007\/s10664-025-10792-1","article-title":"XMutant: XAI-based fuzzing for deep learning systems","volume":"31","author":"Chen","year":"2026","journal-title":"Empir. Software Eng."},{"key":"10.1016\/j.scico.2026.103502_bib0034","series-title":"2025 IEEE\/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)","first-page":"630","article-title":"Test input validation for vision-based dl systems: an active learning approach","author":"Ghobari","year":"2025"},{"key":"10.1016\/j.scico.2026.103502_bib0035","series-title":"2026 IEEE Conference on Software Testing, Verification and Validation (ICST)","article-title":"DEEPNAQQAL: human-aligned automated validation of test inputs for deep learning","author":"Maryam","year":"2026"},{"issue":"4","key":"10.1016\/j.scico.2026.103502_bib0036","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/TR.2021.3074750","article-title":"Supporting deep neural network safety analysis and retraining through heatmap-based unsupervised learning","volume":"70","author":"Fahmy","year":"2021","journal-title":"IEEE Trans. Reliab."},{"key":"10.1016\/j.scico.2026.103502_bib0037","series-title":"2023 ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM)","first-page":"1","article-title":"An empirical study on low-and high-level explanations of deep learning misbehaviours","author":"Zohdinasab","year":"2023"},{"key":"10.1016\/j.scico.2026.103502_bib0038","unstructured":"S. Kang, R. Feldt, S. Yoo, VAE training code for MNIST, 2020, https:\/\/github.com\/coinse\/SINVAD\/blob\/master\/vae\/train.py. Accessed: August 1, 2023."},{"key":"10.1016\/j.scico.2026.103502_bib0039","unstructured":"PyTorch, DCGAN example in pytorch, 2025. https:\/\/github.com\/pytorch\/examples\/blob\/main\/dcgan\/main.py."},{"key":"10.1016\/j.scico.2026.103502_bib0040","unstructured":"Zokovie, cDCGAN-MNIST, 2025, https:\/\/github.com\/zokovi\/cDCGAN-MNIST. Accessed: September 3, 2023."},{"key":"10.1016\/j.scico.2026.103502_bib0041","unstructured":"B. Maltais, Kohya SS - LoRA GUI code, 2025, https:\/\/github.com\/bmaltais\/kohya_ss\/blob\/master\/kohya_gui\/lora_gui.py. Accessed: November 30, 2023."},{"key":"10.1016\/j.scico.2026.103502_bib0042","unstructured":"S. Kang, R. Feldt, S. Yoo, VAE convolutional training code, 2023, https:\/\/github.com\/coinse\/SINVAD\/blob\/master\/vae\/train_conv.py. Accessed: September 29, 2023."},{"key":"10.1016\/j.scico.2026.103502_bib0043","unstructured":"M. Bhandari, Training VAE on ImageNet with PyTorch, 2024, https:\/\/www.kaggle.com\/code\/maunish\/training-vae-on-imagenet-pytorch. Accessed: April 2024."},{"key":"10.1016\/j.scico.2026.103502_bib0044","series-title":"International Conference on Learning Representations","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2019"},{"key":"10.1016\/j.scico.2026.103502_bib0045","series-title":"2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE)","first-page":"355","article-title":"DEEPMETIS: augmenting a deep learning test set to increase its mutation score","author":"Riccio","year":"2021"},{"issue":"12","key":"10.1016\/j.scico.2026.103502_bib0046","doi-asserted-by":"crossref","first-page":"3307","DOI":"10.1109\/TSE.2024.3482984","article-title":"TEASMA: a practical methodology for test adequacy assessment of deep neural networks","volume":"50","author":"Abbasishahkoo","year":"2024","journal-title":"IEEE Trans. Software Eng."},{"key":"10.1016\/j.scico.2026.103502_bib0047","series-title":"Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","first-page":"876","article-title":"Model-based exploration of the frontier of behaviours for deep learning system testing","author":"Riccio","year":"2020"},{"key":"10.1016\/j.scico.2026.103502_bib0048","series-title":"Proceedings of the 30th ACM SIGSOFT International Symposium on Software Testing and Analysis","first-page":"79","article-title":"DeepHyperion: exploring the feature space of deep learning-based systems through illumination search","author":"Zohdinasab","year":"2021"},{"issue":"5","key":"10.1016\/j.scico.2026.103502_bib0049","doi-asserted-by":"crossref","first-page":"3182","DOI":"10.1109\/TSE.2023.3243522","article-title":"Black-box testing of deep neural networks through test case diversity","volume":"49","author":"Aghababaeyan","year":"2023","journal-title":"IEEE Trans. Software Eng."}],"container-title":["Science of Computer Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167642326000687?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167642326000687?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T07:24:54Z","timestamp":1780298694000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167642326000687"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":49,"alternative-id":["S0167642326000687"],"URL":"https:\/\/doi.org\/10.1016\/j.scico.2026.103502","relation":{},"ISSN":["0167-6423"],"issn-type":[{"value":"0167-6423","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"GIFTbench: Generative image fuzz testing benchmark","name":"articletitle","label":"Article Title"},{"value":"Science of Computer Programming","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.scico.2026.103502","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103502"}}