{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T10:39:36Z","timestamp":1789468776425,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373137","type":"print"},{"value":"9783032373144","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\/978-3-032-37314-4_32","type":"book-chapter","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T09:05:46Z","timestamp":1789463146000},"page":"581-598","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["From Masks to\u00a0Pixels and\u00a0Meaning: A New Taxonomy, Benchmark, and\u00a0Metrics for\u00a0VLM Image Tampering"],"prefix":"10.1007","author":[{"given":"Xinyi","family":"Shang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacheng","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Elhagry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salwa K.","family":"Al Khatib","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sondos Mahmoud","family":"Bsharat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing-Hao","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"32_CR1","unstructured":"Azad, R., Heidary, M., Yilmaz, K., H\u00fcttemann, M., Karimijafarbigloo, S., Wu, Y., Schmeink, A., Merhof, D.: Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook (2023). arXiv:2312.05391 arXiv preprint"},{"key":"32_CR2","unstructured":"Chang, Y.M., Yeh, C., Chiu, W.C., Yu, N.: Antifakeprompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors (2023). arXiv:2310.17419 arXiv preprint"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, Y., Song, Y., Liu, L., Wang, J.: Self-supervised learning of adversarial example: towards good generalizations for deepfake detection. In: CVPR, pp. 18710\u201318719 (2022)","DOI":"10.1109\/CVPR52688.2022.01815"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, H., Guo, Y., Wang, T., Nie, L., Kankanhalli, M.: Diffusion facial forgery detection. In: ACM MM, pp. 5939\u20135948 (2024)","DOI":"10.1145\/3664647.3680797"},{"key":"32_CR5","unstructured":"Comanici, G., Bieber, E., Schaekermann, M., Pasupat, I., Sachdeva, N., Dhillon, I., Blistein, M., Ram, O., Zhang, D., Rosen, E.: Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025). arXiv:2507.06261 arXiv preprint"},{"key":"32_CR6","first-page":"49250","volume":"36","author":"W Dai","year":"2023","unstructured":"Dai, W., Li, J., Li, D., Tiong, A., Zhao, J., Wang, W., Li, B., Fung, P.N., Hoi, S.: Instructblip: towards general-purpose vision-language models with instruction tuning. NeurIPS 36, 49250\u201349267 (2023)","journal-title":"NeurIPS"},{"issue":"6","key":"32_CR7","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981)","journal-title":"Commun. ACM"},{"key":"32_CR8","unstructured":"Google AI for Developers: Gemini 3 pro Image Preview (gemini api model documentation) (2026). https:\/\/ai.google.dev\/gemini-api\/docs\/models\/gemini-3-pro-image-preview, model ID: gemini-3-pro-image-preview. Accessed: 27 Feb 2026"},{"key":"32_CR9","unstructured":"Google Cloud: Gemini 2.5 Flash Image (vertex ai model documentation) (2026). https:\/\/docs.cloud.google.com\/vertex-ai\/generative-ai\/docs\/models\/gemini\/2-5-flash-image, model ID: gemini-2.5-flash-image. Accessed: 2026-02-27"},{"issue":"5","key":"32_CR10","doi-asserted-by":"publisher","first-page":"2670","DOI":"10.1007\/s11263-024-02255-9","volume":"133","author":"X Guo","year":"2025","unstructured":"Guo, X., Liu, X., Masi, I., Liu, X.: Language-guided hierarchical fine-grained image forgery detection and localization. Int. J. Comput. Vision 133(5), 2670\u20132691 (2025)","journal-title":"Int. J. Comput. Vision"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Guo, X., Liu, X., Ren, Z., Grosz, S., Masi, I., Liu, X.: Hierarchical fine-grained image forgery detection and localization. In: CVPR, pp. 3155\u20133165 (2023)","DOI":"10.1109\/CVPR52729.2023.00308"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, P., Ghosh, S., Gedeon, T., Do, T.T., Dhall, A.: Multiverse Through Deepfakes: The Multifakeverse Dataset of Person-Centric Visual and Conceptual Manipulations (2025). arXiv:2506.00868 arXiv preprint","DOI":"10.1145\/3746027.3758283"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, V., Ross, C., Pantoja, D., Passonneau, R.J., Ung, M., Williams, A.: Improving model evaluation using smart filtering of benchmark datasets. In: NAACL, pp. 4595\u20134615 (2025)","DOI":"10.18653\/v1\/2025.naacl-long.235"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Z., Hu, J., Li, X., He, Y., Zhao, X., Peng, B., Wu, B., Huang, X., Cheng, G.: Sida: Social media image deepfake detection, localization and explanation with large multimodal model. In: CVPR, pp. 28831\u201328841 (2025)","DOI":"10.1109\/CVPR52734.2025.02685"},{"key":"32_CR16","unstructured":"Labs, B.F.: FLUX.2: Frontier Visual Intelligence (2025). https:\/\/bfl.ai\/blog\/flux-2. Accessed 27 Feb 2026"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Lai, X., Tian, Z., Chen, Y., Li, Y., Yuan, Y., Liu, S., Jia, J.: Lisa: Reasoning segmentation via large language model. In: CVPR, pp. 9579\u20139589 (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Lin, L., Santosh, S., Wu, M., Wang, X., Hu, S.: Ai-face: A million-scale demographically annotated AI-generated face dataset and fairness benchmark. In: CVPR, pp. 3503\u20133515 (2025)","DOI":"10.1109\/CVPR52734.2025.00332"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: ECCV, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"32_CR20","doi-asserted-by":"publisher","first-page":"25435","DOI":"10.52202\/075280-1105","volume":"36","author":"Z Lu","year":"2023","unstructured":"Lu, Z., Huang, D., Bai, L., Qu, J., Wu, C., Liu, X., Ouyang, W.: Seeing is not always believing: benchmarking human and model perception of AI-generated images. Adv. Neural Inf. Proc. Syst. 36, 25435\u201325447 (2023)","journal-title":"Adv. Neural Inf. Proc. Syst."},{"issue":"2","key":"32_CR21","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1192\/bjp.2023.136","volume":"224","author":"S Monteith","year":"2024","unstructured":"Monteith, S., Glenn, T., Geddes, J.R., Whybrow, P.C., Achtyes, E., Bauer, M.: Artificial intelligence and increasing misinformation. Br. J. Psychiatry 224(2), 33\u201335 (2024)","journal-title":"Br. J. Psychiatry"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Nandi, S., Natarajan, P., Abd-Almageed, W.: Trainfors: a large benchmark training dataset for image manipulation detection and localization. In: ICCV, pp. 403\u2013414 (2023)","DOI":"10.1109\/ICCVW60793.2023.00047"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Nguyen, H.H., Yamagishi, J., Echizen, I.: Capsule-forensics: using capsule networks to detect forged images and videos. ICASSP, pp. 2307\u20132311 (2019)","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"32_CR24","unstructured":"OpenAI: GPT Image 1.5 (model documentation) (2026). https:\/\/developers.openai.com\/api\/docs\/models\/gpt-image-1.5, model ID: gpt-image-1.5. Accessed: 24 Feb 2026"},{"key":"32_CR25","first-page":"118025","volume":"37","author":"A Pal","year":"2024","unstructured":"Pal, A., Kruk, J., Phute, M., Bhattaram, M., Yang, D., Chau, D.H., Hoffman, J.: Semi-truths: a large-scale dataset of AI-augmented images for evaluating robustness of AI-generated image detectors. NeurIPS 37, 118025\u2013118051 (2024)","journal-title":"NeurIPS"},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Rahman, M.A., Paul, B., Sarker, N.H., Hakim, Z.I.A., Fattah, S.A.: Artifact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image Detection, pp. 2200\u20132204 . ICIP (2023)","DOI":"10.1109\/ICIP49359.2023.10222083"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Schinas, M., Papadopoulos, S.: Sidbench: A python framework for reliably assessing synthetic image detection methods. In: Proceedings of the 3rd ACM International Workshop on Multimedia AI against Disinformation, pp. 55\u201364 (2024)","DOI":"10.1145\/3643491.3660277"},{"key":"32_CR29","unstructured":"Seedream, T., Chen, Y., Gao, Y.: Seedream 4.0: Toward Next-Generation Multimodal Image Generation (2025). arXiv:2509.20427 arXiv preprint"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Tan, C., Zhao, Y., Wei, S., Gu, G., Wei, Y.: Learning on gradients: Generalized artifacts representation for GAN-generated images detection. In: CVPR, pp. 12105\u201312114 (2023)","DOI":"10.1109\/CVPR52729.2023.01165"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Wang, S.Y., Wang, O., Zhang, R., Owens, A., Efros, A.A.: Cnn-generated images are surprisingly easy to spot... for now. In: CVPR, pp. 8695\u20138704 (2020)","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"32_CR32","unstructured":"Wu, C., Li, J., Zhou, J., Lin, J., Gao, K., Yan, K., Yin, S.m., Bai, S., Xu, X., Chen, Y., et\u00a0al.: Qwen-Image Technical Report (2025). arXiv preprint arXiv:2508.02324"},{"key":"32_CR33","doi-asserted-by":"crossref","unstructured":"Xia, Z., Han, D., Han, Y., Pan, X., Song, S., Huang, G.: Gsva: Generalized segmentation via multimodal large language models. In: CVPR, pp. 3858\u20133869 (2024)","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"32_CR34","doi-asserted-by":"crossref","unstructured":"Xu, D., Fan, S., Kankanhalli, M.: Combating misinformation in the era of generative AI models. In: ACM MM, pp. 9291\u20139298 (2023)","DOI":"10.1145\/3581783.3612704"},{"key":"32_CR35","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 (2024). arXiv preprint arXiv:2410.02761"},{"key":"32_CR36","unstructured":"Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., Lv, C., et\u00a0al.: Qwen3 Technical Report (2025). arXiv preprint arXiv:2505.09388"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, C., Pan, F., Kim, J., Kweon, I.S., Mao, C.: Imagenet-d: benchmarking neural network robustness on diffusion synthetic object. In: CVPR, pp. 21752\u201321762 (2024)","DOI":"10.1109\/CVPR52733.2024.02055"},{"key":"32_CR38","unstructured":"Zhong, N., Xu, Y., Qian, Z., Zhang, X.: Rich and Poor Texture Contrast: A Simple Yet Effective Approach for AI-Generated Image Detection. CoRR (2023)"},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, M., Chen, H., Yan, Q., Huang, X., Lin, G., Li, W., Tu, Z., Hu, H., Hu, J., Wang, Y.: Genimage: A Million-Scale Benchmark for Detecting AI-Generated Image, vol.\u00a036, pp. 77771\u201377782 (2023)","DOI":"10.52202\/075280-3398"},{"key":"32_CR40","doi-asserted-by":"crossref","unstructured":"Zingarini, G., Cozzolino, D., Corvi, R., Poggi, G., Verdoliva, L.: M3dsynth: A Dataset of Medical 3D Images with AI-Generated Local Manipulations, pp. 13176\u201313180. ICASSP (2024)","DOI":"10.1109\/ICASSP48485.2024.10446605"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37314-4_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T09:06:09Z","timestamp":1789463169000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37314-4_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373137","9783032373144"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37314-4_32","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":"16 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}