{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:33:02Z","timestamp":1770334382776,"version":"3.49.0"},"reference-count":31,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Economic Development of the Russian Federation","award":["139-15-2025-012"],"award-info":[{"award-number":["139-15-2025-012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>This paper proposes a novel method for transferable adversarial attacks from Image Quality Assessment (IQA) to Video Quality Assessment (VQA) models. Attacking modern VQA models is challenging due to their high complexity and the temporal nature of video content. Since IQA and VQA models share similar low- and mid-level feature representations, and IQA models are substantially cheaper and faster to run, we leverage them as surrogates to generate transferable adversarial perturbations. Our method, MaxT-I2VQA jointly Maximizes IQA scores and Targets IQA feature activations to improve transferability from IQA to VQA models. We first analyze the correlation between IQA and VQA internal features and use these insights to design a feature-targeting loss. We evaluate MaxT-I2VQA by transferring attacks from four state-of-the-art IQA models to four recent VQA models and compare against three competitive baselines. Compared to prior methods, MaxT-I2VQA increases the transferability of an attack success rate by 7.9% and reduces per-example attack runtime by 8 times. Our experiments confirm that IQA and VQA feature spaces are sufficiently aligned to enable effective cross-task transfer.<\/jats:p>","DOI":"10.3390\/bdcc10020050","type":"journal-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:13:01Z","timestamp":1770289981000},"page":"50","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Transferability of Adversarial Attacks via Maximization and Targeting from Image to Video Quality Assessment"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7176-703X","authenticated-orcid":false,"given":"Georgii","family":"Gotin","sequence":"first","affiliation":[{"name":"AI Center, Lomonosov Moscow State University, Lomonosovsky ave 27b1, Moscow 119991, Russia"},{"name":"Faculty CMC, Lomonosov Moscow State University, GSP-1, Leninskie Gory, Moscow 119991, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6453-5616","authenticated-orcid":false,"given":"Ekaterina","family":"Shumitskaya","sequence":"additional","affiliation":[{"name":"AI Center, Lomonosov Moscow State University, Lomonosovsky ave 27b1, Moscow 119991, Russia"},{"name":"Institute for Artificial Intelligence, Lomonosov Moscow State University, Lomonosovsky ave 27b1, Moscow 119991, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8893-9340","authenticated-orcid":false,"given":"Dmitriy","family":"Vatolin","sequence":"additional","affiliation":[{"name":"AI Center, Lomonosov Moscow State University, Lomonosovsky ave 27b1, Moscow 119991, Russia"},{"name":"Faculty CMC, Lomonosov Moscow State University, GSP-1, Leninskie Gory, Moscow 119991, Russia"},{"name":"Institute for Artificial Intelligence, Lomonosov Moscow State University, Lomonosovsky ave 27b1, Moscow 119991, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1272-5135","authenticated-orcid":false,"given":"Anastasia","family":"Antsiferova","sequence":"additional","affiliation":[{"name":"AI Center, Lomonosov Moscow State University, Lomonosovsky ave 27b1, Moscow 119991, Russia"},{"name":"Institute for Artificial Intelligence, Lomonosov Moscow State University, Lomonosovsky ave 27b1, Moscow 119991, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Antsiferova, A., Abud, K., Gushchin, A., Shumitskaya, E., Lavrushkin, S., and Vatolin, D. (2024, January 20\u201327). Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i2.27827"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Shumitskaya, E., Antsiferova, A., and Vatolin, D. (2023, January 5). Fast Adversarial CNN-based Perturbation Attack on No-Reference Image- and Video-Quality Metrics. Proceedings of the Tiny Papers ICLR, Kigali, Rwanda.","DOI":"10.1016\/j.cviu.2023.103913"},{"key":"ref_3","unstructured":"Shumitskaya, E., Antsiferova, A., and Vatolin, D.S. (2022, January 21\u201324). Universal Perturbation Attack on Differentiable No-Reference Image- and Video-Quality Metrics. Proceedings of the 33rd British Machine Vision Conference, London, UK."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Shumitskaya, T. (2024). Towards adversarial robustness verification of no-reference image- and video-quality metrics. Comput. Vis. Image Underst., 240.","DOI":"10.1016\/j.cviu.2023.103913"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wei, Z., Chen, J., Wu, Z., and Jiang, Y.-G. (2022, January 19\u201324). Cross-Modal Transferable Adversarial Attacks from Images to Videos. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01464"},{"key":"ref_6","unstructured":"Yang, H., Jeong, J., and Yoon, K.-J. (October, January 29). Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks. Proceedings of the 18th European Conference on Computer Vision, Milan, Italy."},{"key":"ref_7","unstructured":"Aich, A., Ta, C.-K., Gupta, A., Song, C., Krishnamurthy, S., Asif, S., and Roy-Chowdhury, A. (December, January 28). GAMA: Generative Adversarial Multi-Object Scene Attacks. Proceedings of the 35th Advances in Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_8","first-page":"2635","article-title":"Global-Local Characteristic Excited Cross-Modal Attacks from Images to Videos","volume":"37","author":"Wang","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Gotin, G., Shumitskaya, E., Antsiferova, A., and Vatolin, D. (2025, January 26\u201328). Cross-Modal Transferable Image-to-Video Attack on Video Quality Metrics. Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications\u2014Volume 3: VISAPP, Porto, Portugal.","DOI":"10.5220\/0013387000003912"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18\u201322). The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref_11","unstructured":"(2025, October 01). VMAF: Perceptual Video Quality Assessment Based on Multi-Method Fusion. Available online: https:\/\/github.com\/Netflix\/vmaf."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ying, Z., Niu, H., Gupta, P., Mahajan, D., Ghadiyaram, D., and Bovik, A. (2020, January 16\u201322). From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Los Alamitos, CA, USA.","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3998","DOI":"10.1109\/TIP.2018.2831899","article-title":"NIMA: Neural Image Assessment","volume":"27","author":"Talebi","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Fang, Y., Zhu, H., Zeng, Y., Ma, K., and Wang, Z. (2020, January 16\u201318). Perceptual Quality Assessment of Smartphone Photography. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Los Alamitos, CA, USA.","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1109\/TCSVT.2018.2886771","article-title":"Blind Image Quality Assessment Using a Deep Bilinear Convolutional Neural Network","volume":"30","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li, D., Jiang, T., and Jiang, M. (2020, January 12\u201316). Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessment. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA.","DOI":"10.1145\/3394171.3413804"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, D., Jiang, T., and Jiang, M. (2019, January 21\u201325). Quality Assessment of In-the-Wild Videos. Proceedings of the 27th ACM International Conference on Multimedia, Nice, France.","DOI":"10.1145\/3343031.3351028"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wu, H., Zhang, E., Liao, L., Chen, C., Hou, J.H., Wang, A., Sun, W.S., Yan, Q., and Lin, W. (2023, January 2\u20133). Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1007\/s11263-020-01408-w","article-title":"Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training","volume":"129","author":"Li","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, A.-X., and Wang, Y.-G. (2022, January 22\u201327). Texture Information Boosts Video Quality Assessment. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore.","DOI":"10.1109\/ICASSP43922.2022.9747546"},{"key":"ref_21","unstructured":"Goodfellow, I.J., Shlens, J., and Szegedy, C. (2015, January 7\u20139). Explaining and Harnessing Adversarial Examples. Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_22","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., and Vladu, A. (May, January 30). Towards Deep Learning Models Resistant to Adversarial Attacks. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_23","unstructured":"Leonenkova, V., Shumitskaya, E., Antsiferova, A., and Vatolin, D. (2024). Ti-Patch: Tiled Physical Adversarial Patch for no-reference video quality metrics. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Shumitskaya, E., Antsiferova, A., and Vatolin, D.S. (2024, January 21\u201327). IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics. Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria.","DOI":"10.1016\/j.cviu.2023.103913"},{"key":"ref_25","unstructured":"Zhang, W., Li, D., Min, X., Zhai, G., Guo, G., Yang, X., and Ma, K. (December, January 28). Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop. Proceedings of the 36th International Conference on Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yang, C., Li, D., Ding, J., and Jiang, T. (2024, January 17\u201321). Defense against adversarial attacks on no-reference image quality models with gradient norm regularization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02414"},{"key":"ref_27","unstructured":"Zhang, A.-X., Ran, Y., Tang, W., and Wang, Y.-G. (2023, January 10\u201316). Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks. Proceedings of the 37th International Conference on Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Andriushchenko, M., Croce, F., Flammarion, N., and Hein, M. (2020, January 23\u201328). Square Attack: A query-efficient black-box adversarial attack via random search. Proceedings of the Computer Vision\u2014ECCV 2020, SEC, Glasgow, UK.","DOI":"10.1007\/978-3-030-58592-1_29"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Lin, H., Hosu, V., and Saupe, D. (2019, January 5\u20137). KADID-10k: A Large-scale Artificially Distorted IQA Database. Proceedings of the 11th International Conference on Quality of Multimedia Experience, Berlin, Germany.","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"ref_30","unstructured":"(2025, October 01). Xiph.org Video Test Media. Available online: https:\/\/media.xiph.org\/video\/derf\/."},{"key":"ref_31","unstructured":"Antsiferova, A., Lavrushkin, S., Smirnov, M., Gushchin, A., Vatolin, D., and Kulikov, D. (December, January 28). Video compression dataset and benchmark of learning-based video-quality metrics. Proceedings of the 35th Advances in Neural Information Processing Systems, New Orleans, LA, USA."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/2\/50\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:42:31Z","timestamp":1770291751000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/2\/50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["bdcc10020050"],"URL":"https:\/\/doi.org\/10.3390\/bdcc10020050","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,5]]}}}