{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T11:10:07Z","timestamp":1750677007776,"version":"3.41.0"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"DOI":"10.1007\/s10462-025-11184-z","type":"journal-article","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T05:19:02Z","timestamp":1748236742000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards few-call model stealing via active self-paced knowledge distillation and diffusion-based image generation"],"prefix":"10.1007","volume":"58","author":[{"given":"Vlad","family":"Hondru","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radu Tudor","family":"Ionescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,26]]},"reference":[{"key":"11184_CR1","doi-asserted-by":"crossref","unstructured":"Addepalli S, Nayak GK, Chakraborty A, et\u00a0al. (2020) DeGAN: data-enriching GAN for retrieving representative samples from a trained classifier. In: Proceedings of AAAI, pp 3130\u20133137, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/5709","DOI":"10.1609\/aaai.v34i04.5709"},{"key":"11184_CR2","unstructured":"Amit T, Nachmani E, Shaharbany T, et\u00a0al. (2021) SegDiff: image segmentation with diffusion probabilistic models. arXiv preprint arXiv:2112.00390"},{"key":"11184_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami O, Lischinski D, Fried O (2022) Blended diffusion for text-driven editing of natural images. In: Proceedings of CVPR, pp 18208\u201318218, https:\/\/ieeexplore.ieee.org\/document\/9879075","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"11184_CR4","unstructured":"Baranchuk D, Rubachev I, Voynov A, et\u00a0al. (2022) Label-efficient semantic segmentation with diffusion models. In: Proceedings of ICLR, https:\/\/openreview.net\/pdf?id=SlxSY2UZQT"},{"key":"11184_CR5","unstructured":"B\u0103rb\u0103l\u0103u A, Cosma A, Ionescu RT, et\u00a0al. (2020) Black-box ripper: Copying black-box models using generative evolutionary algorithms. In: Proceedings of NeurIPS, pp 20120\u201320129, https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/e8d66338fab3727e34a9179ed8804f64-Paper.pdf"},{"key":"11184_CR6","doi-asserted-by":"crossref","unstructured":"Barsoum E, Zhang C, Canton\u00a0Ferrer C, et\u00a0al. (2016) Training deep networks for facial expression recognition with crowd-sourced label distribution. In: Proceedings of ICMI, pp 279\u2013283, https:\/\/dl.acm.org\/doi\/10.1145\/2993148.2993165","DOI":"10.1145\/2993148.2993165"},{"key":"11184_CR7","doi-asserted-by":"crossref","unstructured":"Biggio B, Corona I, Maiorca D, et\u00a0al. (2013) Evasion attacks against machine learning at test time. In: Proceedings of PKDD, pp 387\u2013402, https:\/\/link.springer.com\/chapter\/10.1007\/978-3-642-40994-3_25","DOI":"10.1007\/978-3-642-40994-3_25"},{"key":"11184_CR8","doi-asserted-by":"crossref","unstructured":"Bossard L, Guillaumin M, Van\u00a0Gool L (2014) Food-101\u2013 mining discriminative components with random forests. In: Proceedings of ECCV, pp 446\u2013461, https:\/\/link.springer.com\/chapter\/10.1007\/978-3-319-10599-4_29","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"11184_CR9","unstructured":"Chandrasekaran V, Chaudhuri K, Giacomelli I, et\u00a0al. (2020) Exploring connections between active learning and model extraction. In: Proceedings of USENIX, pp 1309\u20131326, https:\/\/www.usenix.org\/system\/files\/sec20-chandrasekaran.pdf"},{"key":"11184_CR10","unstructured":"Chen H, Quan X, Chen H, et\u00a0al. (2024) Knowledge distillation for closed-source language models. arXiv preprint arXiv:2401.07013"},{"key":"11184_CR11","doi-asserted-by":"crossref","unstructured":"Correia-Silva JR, Berriel RF, Badue C, et\u00a0al. (2018) Copycat CNN: stealing knowledge by persuading confession with random non-labeled data. In: Proceedings of IJCNN, pp 1\u20138, https:\/\/ieeexplore.ieee.org\/document\/8489592","DOI":"10.1109\/IJCNN.2018.8489592"},{"issue":"9","key":"11184_CR12","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"FA Croitoru","year":"2023","unstructured":"Croitoru FA, Hondru V, Ionescu RT et\u00a0al. (2023) Diffusion models in vision: a survey. IEEE Trans Pattern Anal Mach Intell 45(9):10850\u201310869","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11184_CR13","unstructured":"Dhariwal P, Nichol A (2021) Diffusion models beat GANs on image synthesis. In: Proceedings of NeurIPS, pp 8780\u20138794, https:\/\/papers.nips.cc\/paper_files\/paper\/2021\/file\/49ad23d1ec9fa4bd8d77d02681df5cfa-Paper.pdf"},{"key":"11184_CR14","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et\u00a0al. (2021) An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of ICLR, https:\/\/openreview.net\/pdf?id=YicbFdNTTy"},{"key":"11184_CR15","doi-asserted-by":"crossref","unstructured":"Fang G, Song J, Wang X, et\u00a0al. (2021) Contrastive model inversion for data-free knowledge distillation. In: Proceedings of IJCAI, pp 2374\u20132380, https:\/\/www.ijcai.org\/proceedings\/2021\/0327.pdf","DOI":"10.24963\/ijcai.2021\/327"},{"key":"11184_CR16","doi-asserted-by":"crossref","unstructured":"Goodfellow IJ, Erhan D, Carrier PL, et\u00a0al. (2013) Challenges in representation learning: a report on three machine learning contests. In: Proceedings of ICONIP, pp 117\u2013124, https:\/\/link.springer.com\/chapter\/10.1007\/978-3-642-42051-1_16","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"11184_CR17","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, et\u00a0al. (2014a) Generative adversarial nets. In: Proceedings of NeurIPS, pp 2672\u20132680, https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2014\/file\/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf"},{"key":"11184_CR18","unstructured":"Goodfellow I, Shlens J, Szegedy C (2014b) Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572"},{"key":"11184_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et\u00a0al. (2016) Deep residual learning for image recognition. In: Proceedings of CVPR, pp 770\u2013778, https:\/\/ieeexplore.ieee.org\/document\/7780459","DOI":"10.1109\/CVPR.2016.90"},{"key":"11184_CR20","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. In: Proceedings of NeurIPS, pp 6840\u20136851, https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf"},{"key":"11184_CR21","unstructured":"Jagielski M, Carlini N, Berthelot D, et\u00a0al. (2020) High accuracy and high fidelity extraction of neural networks. In: Proceedings of USENIX, pp 1345\u20131362, https:\/\/www.usenix.org\/system\/files\/sec20fall_jagielski_prepub.pdf"},{"key":"11184_CR22","doi-asserted-by":"crossref","unstructured":"Juuti M, Szyller S, Marchal S, et\u00a0al. (2019) PRADA: protecting against DNN model stealing attacks. In: Proceedings of EuroS &P, pp 512\u2013527, https:\/\/ieeexplore.ieee.org\/document\/8806737","DOI":"10.1109\/EuroSP.2019.00044"},{"key":"11184_CR23","doi-asserted-by":"crossref","unstructured":"Kariyappa S, Prakash A, Qureshi MK (2021) MAZE: data-free model stealing attack using zeroth-order gradient estimation. In: Proceedings of CVPR, pp 13814\u201313823, https:\/\/ieeexplore.ieee.org\/document\/9577631","DOI":"10.1109\/CVPR46437.2021.01360"},{"key":"11184_CR24","doi-asserted-by":"crossref","unstructured":"Kesarwani M, Mukhoty B, Arya V, et\u00a0al. (2018) Model extraction warning in MLaaS paradigm. In: Proceedings of ACSAC, pp 371\u2013380, https:\/\/dl.acm.org\/doi\/10.1145\/3274694.3274740","DOI":"10.1145\/3274694.3274740"},{"key":"11184_CR25","unstructured":"Kingma DP, Ba JL (2015) Adam: a method for stochastic gradient descent. In: Proceedings of ICLR, arXiv:1412.6980"},{"key":"11184_CR26","unstructured":"Krizhevsky A (2009) Learning multiple layers of features from tiny images. Tech. rep., University of Toronto, https:\/\/www.cs.toronto.edu\/~kriz\/learning-features-2009-TR.pdf"},{"key":"11184_CR27","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Proceedings of NeurIPS, https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2012\/file\/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf"},{"key":"11184_CR28","unstructured":"Le Y, Yang X (2015) Tiny ImageNet visual recognition challenge. CS 231N 7(7):3. http:\/\/vision.stanford.edu\/teaching\/cs231n\/reports\/2015\/pdfs\/yle_project.pdf"},{"key":"11184_CR29","doi-asserted-by":"crossref","unstructured":"Liu X, Ma Z, Liu Y, et\u00a0al. (2022) SeInspect: Defending model stealing via heterogeneous semantic inspection. In: Proceedings of ESORICS, pp 610\u2013630, https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-17140-6_30","DOI":"10.1007\/978-3-031-17140-6_30"},{"key":"11184_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119202","volume":"642","author":"J Li","year":"2023","unstructured":"Li J, Zhou S, Li L et\u00a0al. (2023) Dynamic data-free knowledge distillation by easy-to-hard learning strategy. Inf Sci 642:119202","journal-title":"Inf Sci"},{"key":"11184_CR31","doi-asserted-by":"crossref","unstructured":"Lugmayr A, Danelljan M, Romero A, et\u00a0al. (2022) RePaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of CVPR, pp 11461\u201311471, https:\/\/ieeexplore.ieee.org\/document\/9880056","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"11184_CR32","unstructured":"Micaelli P, Storkey AJ (2019) Zero-shot knowledge transfer via adversarial belief matching. In: Proceedings of NeurIPS, pp 9551\u20139561, https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/fe663a72b27bdc613873fbbb512f6f67-Paper.pdf"},{"key":"11184_CR33","doi-asserted-by":"crossref","unstructured":"Mosafi I, David EO, Netanyahu NS (2019) Stealing knowledge from protected deep neural networks using composite unlabeled data. In: Proceedings of IJCNN, pp 1\u20138, https:\/\/ieeexplore.ieee.org\/document\/8851798","DOI":"10.1109\/IJCNN.2019.8851798"},{"key":"11184_CR34","unstructured":"Nayak GK, Mopuri KR, Shaj V, et\u00a0al. (2019) Zero-shot knowledge distillation in deep networks. In: Proceedings of ICML, pp 4743\u20134751, http:\/\/proceedings.mlr.press\/v97\/nayak19a.html"},{"key":"11184_CR35","unstructured":"Nichol AQ, Dhariwal P (2021) Improved denoising diffusion probabilistic models. In: Proceedings of ICML, pp 8162\u20138171, https:\/\/proceedings.mlr.press\/v139\/nichol21a.html"},{"key":"11184_CR36","unstructured":"Nichol A, Dhariwal P, Ramesh A, et\u00a0al. (2021) GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models. In: Proceedings of ICML, pp 16784\u201316804, https:\/\/proceedings.mlr.press\/v162\/nichol22a.html"},{"key":"11184_CR37","doi-asserted-by":"crossref","unstructured":"Oh SJ, Schiele B, Fritz M (2019) Towards reverse-engineering black-box neural networks. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning pp 121\u2013144. https:\/\/link.springer.com\/chapter\/10.1007\/978-3-030-28954-6_7","DOI":"10.1007\/978-3-030-28954-6_7"},{"key":"11184_CR38","doi-asserted-by":"publisher","DOI":"10.1145\/3595292","author":"D Oliynyk","year":"2023","unstructured":"Oliynyk D, Mayer R, Rauber A (2023) I know what you trained last summer: a survey on stealing machine learning models and defences. ACM Comput Surv. https:\/\/doi.org\/10.1145\/3595292","journal-title":"ACM Comput Surv"},{"key":"11184_CR39","unstructured":"OpenAI (2022) Chatgpt: A conversational language model. https:\/\/openai.com\/research\/chatgpt"},{"key":"11184_CR40","doi-asserted-by":"crossref","unstructured":"Orekondy T, Schiele B, Fritz M (2019) Knockoff nets: stealing functionality of black-box models. In: Proceedings of CVPR, pp 4954\u20134963, https:\/\/ieeexplore.ieee.org\/document\/8953839","DOI":"10.1109\/CVPR.2019.00509"},{"key":"11184_CR41","unstructured":"Pal S, Gupta Y, Shukla A, et\u00a0al. (2019) A framework for the extraction of deep neural networks by leveraging public data. arXiv preprint arXiv:1905.09165"},{"key":"11184_CR42","doi-asserted-by":"crossref","unstructured":"Papernot N, McDaniel P, Goodfellow I, et\u00a0al. (2017) Practical black-box attacks against machine learning. In: Proceedings of ASIACCS, pp 506\u2013519, https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3052973.3053009","DOI":"10.1145\/3052973.3053009"},{"key":"11184_CR43","doi-asserted-by":"crossref","unstructured":"Pengcheng L, Yi J, Zhang L (2018) Query-efficient black-box attack by active learning. In: Proceedings of ICDM, pp 1200\u20131205, https:\/\/ieeexplore.ieee.org\/document\/8594968","DOI":"10.1109\/ICDM.2018.00159"},{"key":"11184_CR44","unstructured":"Podell D, English Z, Lacey K, et\u00a0al. (2024) SDXL: improving latent diffusion models for high-resolution image synthesis. In: Proceedings of ICLR, https:\/\/openreview.net\/forum?id=di52zR8xgf"},{"key":"11184_CR45","unstructured":"Radford A, Kim JW, Hallacy C, et\u00a0al. (2021) Learning transferable visual models from natural language supervision. In: Proceedings of ICML, pp 8748\u20138763, http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"11184_CR46","doi-asserted-by":"crossref","unstructured":"Rombach R, Blattmann A, Lorenz D, et\u00a0al. (2022) High-resolution image synthesis with latent diffusion models. In: Proceedings of CVPR, pp 10684\u201310695, https:\/\/ieeexplore.ieee.org\/document\/9878449","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"3","key":"11184_CR47","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H et\u00a0al. (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252. https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int J Comput Vis"},{"key":"11184_CR48","unstructured":"Saharia C, Chan W, Saxena S, et\u00a0al. (2022) Photorealistic Text-to-image diffusion models with deep language understanding. In: Proceedings of NeurIPS, pp 36479\u201336494, https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/ec795aeadae0b7d230fa35cbaf04c041-Paper-Conference.pdf"},{"key":"11184_CR49","doi-asserted-by":"crossref","unstructured":"Sanyal S, Addepalli S, Babu RV (2022) Towards data-free model stealing in a hard label setting. In: Proceedings of CVPR, pp 15284\u201315293, https:\/\/ieeexplore.ieee.org\/document\/9880326","DOI":"10.1109\/CVPR52688.2022.01485"},{"key":"11184_CR50","doi-asserted-by":"crossref","unstructured":"Shi Y, Sagduyu YE, Davaslioglu K, et\u00a0al. (2018) Active deep learning attacks under strict rate limitations for online API calls. In: Proceedings of HST, pp 1\u20136, https:\/\/ieeexplore.ieee.org\/document\/8574124","DOI":"10.1109\/THS.2018.8574124"},{"key":"11184_CR51","doi-asserted-by":"crossref","unstructured":"Shi Y, Sagduyu Y, Grushin A (2017) How to steal a machine learning classifier with deep learning. In: Proceedings of HST, pp 1\u20135, https:\/\/ieeexplore.ieee.org\/document\/7943475","DOI":"10.1109\/THS.2017.7943475"},{"key":"11184_CR52","unstructured":"Sohl-Dickstein J, Weiss E, Maheswaranathan N, et\u00a0al. (2015) Deep unsupervised learning using nonequilibrium thermodynamics. In: Proceedings of ICML, pp 2256\u20132265, https:\/\/proceedings.mlr.press\/v37\/sohl-dickstein15.html"},{"key":"11184_CR53","doi-asserted-by":"publisher","first-page":"3359","DOI":"10.1109\/TIP.2022.3170728","volume":"31","author":"J Song","year":"2022","unstructured":"Song J, Chen Y, Ye J et\u00a0al. (2022) Spot-adaptive knowledge distillation. IEEE Trans Image Process 31:3359\u20133370","journal-title":"IEEE Trans Image Process"},{"key":"11184_CR54","unstructured":"Song J, Meng C, Ermon S (2021) Denoising diffusion implicit models. In: Proceedings of ICLR, https:\/\/openreview.net\/pdf?id=St1giarCHLP"},{"issue":"6","key":"11184_CR55","doi-asserted-by":"publisher","first-page":"1526","DOI":"10.1007\/s11263-022-01611-x","volume":"130","author":"P Soviany","year":"2022","unstructured":"Soviany P, Ionescu RT, Rota P et\u00a0al. (2022) Curriculum learning: a survey. Int J Comput Vis 130(6):1526\u20131565. https:\/\/doi.org\/10.1007\/s11263-022-01611-x","journal-title":"Int J Comput Vis"},{"key":"11184_CR56","unstructured":"Tram\u00e8r F, Zhang F, Juels A, et\u00a0al. (2016) Stealing machine learning models via prediction APIs. In: Proceedings of USENIX, pp 601\u2013618, https:\/\/www.usenix.org\/system\/files\/conference\/usenixsecurity16\/sec16_paper_tramer.pdf"},{"key":"11184_CR57","unstructured":"Vasu PKA, Gabriel J, Zhu J, et\u00a0al. (2023) FastViT: a fast hybrid vision transformer using structural reparameterization. In: Proceedings of ICCV, pp 5785\u20135795, https:\/\/ieeexplore.ieee.org\/abstract\/document\/10377971"},{"key":"11184_CR58","unstructured":"Wang Z (2021) Zero-shot knowledge distillation from a decision-based black-box model. In: Proceedings of ICML, pp 10675\u201310685, https:\/\/proceedings.mlr.press\/v139\/wang21a.html"},{"key":"11184_CR59","doi-asserted-by":"crossref","unstructured":"Wang B, Gong NZ (2018) Stealing hyperparameters in machine learning. In: Proceedings of SP, IEEE, pp 36\u201352, https:\/\/ieeexplore.ieee.org\/document\/8418595","DOI":"10.1109\/SP.2018.00038"},{"key":"11184_CR60","unstructured":"Wei K, Sun X, Zhang Z, et\u00a0al. (2021) Trigger is not sufficient: exploiting frame-aware knowledge for implicit event argument extraction. In: Proceedings of ACL, pp 4672\u20134682, https:\/\/aclanthology.org\/2021.acl-long.360\/"},{"key":"11184_CR61","doi-asserted-by":"crossref","unstructured":"Wolleb J, Bieder F, Sandk\u00fchler R, et\u00a0al. (2022) Diffusion models for medical anomaly detection. In: Proceedings of MICCAI, pp 35\u201345, https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-16452-1_4","DOI":"10.1007\/978-3-031-16452-1_4"},{"key":"11184_CR62","doi-asserted-by":"crossref","unstructured":"Xie Y, Huang M, Zhang X, et\u00a0al. (2022) Game: generative-based adaptive model extraction attack. In: Proceedings of ESORICS, pp 570\u2013588, https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-17140-6_28","DOI":"10.1007\/978-3-031-17140-6_28"},{"issue":"4","key":"11184_CR63","doi-asserted-by":"publisher","first-page":"2680","DOI":"10.1109\/TDSC.2021.3069258","volume":"19","author":"H Yan","year":"2022","unstructured":"Yan H, Li X, Li H et\u00a0al. (2022) Monitoring-based differential privacy mechanism against query flooding-based model extraction attack. IEEE Trans Depend Secure Comput 19(4):2680\u20132694","journal-title":"IEEE Trans Depend Secure Comput"},{"key":"11184_CR64","doi-asserted-by":"crossref","unstructured":"Ye J, Mao Y, Song J, et\u00a0al. (2022) Safe distillation box. In: Proceedings of AAAI, pp 3117\u20133124, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/20219","DOI":"10.1609\/aaai.v36i3.20219"},{"key":"11184_CR65","doi-asserted-by":"crossref","unstructured":"Yin H, Molchanov P, Alvarez JM, et\u00a0al. (2020) Dreaming to distill: data-free knowledge transfer via DeepInversion. In: Proceedings of CVPR, pp 8715\u20138724, https:\/\/ieeexplore.ieee.org\/document\/9156864","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"11184_CR66","unstructured":"Zhang J, Chen C, Lyu L (2023) IDEAL: query-efficient data-free learning from black-box models. In: Proceedings of ICLR, https:\/\/openreview.net\/forum?id=ConT6H7MWL"},{"key":"11184_CR67","doi-asserted-by":"crossref","unstructured":"Zhang Z, Chen Y, Wagner D (2021) SEAT: similarity encoder by adversarial training for detecting model extraction attack queries. In: Proceedings of AISec, pp 37\u201348, https:\/\/dl.acm.org\/doi\/10.1145\/3474369.3486863","DOI":"10.1145\/3474369.3486863"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11184-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-025-11184-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11184-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T10:35:06Z","timestamp":1750674906000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-025-11184-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,26]]},"references-count":67,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["11184"],"URL":"https:\/\/doi.org\/10.1007\/s10462-025-11184-z","relation":{},"ISSN":["1573-7462"],"issn-type":[{"type":"electronic","value":"1573-7462"}],"subject":[],"published":{"date-parts":[[2025,5,26]]},"assertion":[{"value":"28 February 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"The authors give their consent for publication.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"254"}}