{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T12:29:47Z","timestamp":1771244987441,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569496","type":"print"},{"value":"9789819569502","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-6950-2_3","type":"book-chapter","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:59:18Z","timestamp":1771243158000},"page":"32-45","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dissecting Deepfake Artifacts via\u00a0Multimodal Explanations"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1927-4208","authenticated-orcid":false,"given":"Yannan","family":"Bai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danding","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"issue":"1","key":"3_CR1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2110013119","volume":"119","author":"M Groh","year":"2022","unstructured":"Groh, M., Epstein, Z., Firestone, C., Picard, R.: Deepfake detection by human crowds, machines, and machine-informed crowds. Proc. Natl. Acad. Sci. 119(1), e2110013119 (2022)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Hashmi, A., Shahzad, S.A., Lin, C.W., Tsao, Y., Wang, H.M.: Unmasking illusions: understanding human perception of audiovisual deepfakes, arXiv preprint arXiv:2405.04097 (2024)","DOI":"10.36227\/techrxiv.171560542.29368554\/v1"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: Face X-ray for more general face forgery detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5001\u20135010 (2020)","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Li, Y., Chang, M.-C., Lyu, S.: In ictu oculi: exposing AI created fake videos by detecting eye blinking. In: 2018 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1\u20137. IEEE (2018)","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Demir, I., Ciftci, U.A.: Where do deep fakes look? Synthetic face detection via gaze tracking. In: ACM Symposium on Eye Tracking Research and Applications, pp. 1\u201311 (2021)","DOI":"10.1145\/3448017.3457387"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Boyd, A., Tinsley, P., Bowyer, K., Czajka, A.: The value of AI guidance in human examination of synthetically-generated faces. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 5, pp. 5930\u20135938 (2023)","DOI":"10.1609\/aaai.v37i5.25734"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Jia, S., et al.: Can chatgpt detect deepfakes? A study of using multimodal large language models for media forensics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4324\u20134333 (2024)","DOI":"10.1109\/CVPRW63382.2024.00436"},{"key":"3_CR8","unstructured":"Yan, Z., Zhang, Y., Yuan, X., Lyu, S., Wu, B.: Deepfakebench: a comprehensive benchmark of deepfake detection. In: Proceedings of the 37th International Conference on Neural Information Processing Systems, pp. 4534\u20134565 (2023)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Sun, K., et al.: Towards general visual-linguistic face forgery detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 19576\u201319586 (2025)","DOI":"10.1109\/CVPR52734.2025.01823"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Colman, B., Guo, X., Shahriyari, A., Bharaj, G.: Common sense reasoning for deepfake detection. In: European Conference on Computer Vision, pp. 399\u2013415. Springer (2024)","DOI":"10.1007\/978-3-031-73223-2_22"},{"key":"3_CR11","unstructured":"Lu, Z., et al.: Seeing is not always believing: benchmarking human and model perception of AI-generated images. In: Advances in Neural Information Processing Systems, vol.\u00a036, pp. 25435\u201325447 (2023)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Bray, S.D., Johnson, S.D., Kleinberg, B.: Testing human ability to detect \u2018deepfake\u2019 images of human faces. J. Cybersecur. 9, tyad011 (2023)","DOI":"10.1093\/cybsec\/tyad011"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Tahir, R., et al.: Seeing is believing: exploring perceptual differences in DeepFake videos. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, Yokohama Japan, pp. 1\u201316. ACM (2021)","DOI":"10.1145\/3411764.3445699"},{"issue":"4","key":"3_CR14","doi-asserted-by":"publisher","first-page":"2371","DOI":"10.1080\/10447318.2024.2323263","volume":"41","author":"R M\u00fcller","year":"2025","unstructured":"M\u00fcller, R., Tho\u00df, M., Ullrich, J., Seitz, S., Knoll, C.: Interpretability is in the eye of the beholder: human versus artificial classification of image segments generated by humans versus XAI. Int. J. Hum.-Comput. Interact. 41(4), 2371\u20132393 (2025)","journal-title":"Int. J. Hum.-Comput. Interact."},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Boyd, A., Tinsley, P., Bowyer, K., Czajka, A.: The value of AI guidance in human examination of synthetically-generated faces. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 5930\u20135938 (2023)","DOI":"10.1609\/aaai.v37i5.25734"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"3_CR17","first-page":"5922","volume":"33","author":"A Ghorbani","year":"2020","unstructured":"Ghorbani, A., Zou, J.Y.: Neuron shapley: discovering the responsible neurons. Adv. Neural. Inf. Process. Syst. 33, 5922\u20135932 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 782\u2013791 (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Tsigos, K., Apostolidis, E., Baxevanakis, S., Papadopoulos, S., Mezaris, V.: Towards quantitative evaluation of explainable AI methods for deepfake detection. In: Proceedings of the 3rd ACM International Workshop on Multimedia AI Against Disinformation, pp. 37\u201345 (2024)","DOI":"10.1145\/3643491.3660292"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, T., Yu, Z., Gao, Z., Shen, L., Chen, S.: MFCLIP: multi-modal fine-grained clip for generalizable diffusion face forgery detection. IEEE Trans. Inf. Forensics Secur. (2025)","DOI":"10.1109\/TIFS.2025.3576577"},{"key":"3_CR21","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol.\u00a036 (2024)"},{"key":"3_CR22","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. In: ICLR (2024)"},{"key":"3_CR23","first-page":"2943","volume":"37","author":"NM Foteinopoulou","year":"2024","unstructured":"Foteinopoulou, N.M., Ghorbel, E., Aouada, D.: A hitchhiker\u2019s guide to fine-grained face forgery detection using common sense reasoning. Adv. Neural. Inf. Process. Syst. 37, 2943\u20132976 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Forensics-bench: a comprehensive forgery detection benchmark suite for large vision language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 4233\u20134245 (2025)","DOI":"10.1109\/CVPR52734.2025.00400"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhang, X., Li, R., Tang, Z., Huang, Q., Zhang, J.: Fakeshield: explainable image forgery detection and localization via multi-modal large language models. In: International Conference on Learning Representations (2025)","DOI":"10.1109\/ICIP55913.2025.11084582"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: Sida: social media image deepfake detection, localization and explanation with large multimodal model. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 28831\u201328841 (2025)","DOI":"10.1109\/CVPR52734.2025.02685"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Guo, X., Song, X., Zhang, Y., Liu, X., Liu, X.: Rethinking vision-language model in face forensics: multi-modal interpretable forged face detector. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 105\u2013116 (2025)","DOI":"10.1109\/CVPR52734.2025.00019"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nie\u00dfner, M.: Faceforensics++: learning to detect manipulated facial images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1\u201311 (2019)","DOI":"10.1109\/ICCV.2019.00009"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Jiang, L., Li, R., Wu, W., Qian, C., Loy, C.C.: Deeperforensics-1.0: a large-scale dataset for real-world face forgery detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2889\u20132898 (2020)","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"3_CR30","unstructured":"Dolhansky, B., et al.: The deepfake detection challenge (DFDC) dataset, arXiv preprint arXiv:2006.07397 (2020)"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"He, Y., et al.: Forgerynet: a versatile benchmark for comprehensive forgery analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4360\u20134369 (2021)","DOI":"10.1109\/CVPR46437.2021.00434"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Liang, J., Shi, H., Deng, W.: Exploring disentangled content information for face forgery detection. In: European Conference on Computer Vision, pp. 128\u2013145. Springer (2022)","DOI":"10.1007\/978-3-031-19781-9_8"},{"key":"3_CR33","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding, arXiv preprint arXiv:1807.03748 (2018)"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Bisenet: bilateral segmentation network for real-time semantic segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 325\u2013341 (2018)","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Shao, R., Wu, T., Liu, Z.: Detecting and recovering sequential deepfake manipulation. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19778-9_41"},{"key":"3_CR36","unstructured":"Targ, S., Almeida, D., Lyman, K.: Resnet in resnet: generalizing residual architectures, arXiv preprint arXiv:1603.08029 (2016)"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Zhuang, W., et al.: UIA-ViT: Unsupervised inconsistency-aware method based on vision transformer for face forgery detection. In: European Conference on Computer Vision, pp. 391\u2013407. Springer (2022)","DOI":"10.1007\/978-3-031-20065-6_23"},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"Shiohara, K., Yamasaki, T.: Detecting deepfakes with self-blended images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18720\u201318729 (2022)","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Dong, S., Wang, J., Ji, R., Liang, J., Fan, H., Ge, Z.: Implicit identity leakage: the stumbling block to improving deepfake detection generalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3994\u20134004 (2023)","DOI":"10.1109\/CVPR52729.2023.00389"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6950-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:59:28Z","timestamp":1771243168000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6950-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569496","9789819569502"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6950-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"17 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}