{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T21:36:26Z","timestamp":1781472986249,"version":"3.54.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031783043","type":"print"},{"value":"9783031783050","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78305-0_11","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T10:12:24Z","timestamp":1733220744000},"page":"160-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["FIDAVL: Fake Image Detection and Attribution Using Vision-Language Model"],"prefix":"10.1007","author":[{"given":"Mamadou","family":"Keita","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wassim","family":"Hamidouche","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hessen Bougueffa","family":"Eutamene","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdelmalik","family":"Taleb-Ahmed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdenour","family":"Hadid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"11_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Amoroso, R., Morelli, D., Cornia, M., Baraldi, L., Del\u00a0Bimbo, A., Cucchiara, R.: Parents and children: Distinguishing multimodal deepfakes from natural images. arXiv preprint arXiv:2304.00500 (2023)","DOI":"10.1145\/3665497"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Bui, T., Yu, N., Collomosse, J.: Repmix: Representation mixing for robust attribution of synthesized images. In: European Conference on Computer Vision. pp. 146\u2013163. Springer (2022)","DOI":"10.1007\/978-3-031-19781-9_9"},{"key":"11_CR4","unstructured":"Chang, Y.M., Yeh, C., Chiu, W.C., Yu, N.: Antifakeprompt: Prompt-tuned vision-language models are fake image detectors. arXiv preprint arXiv:2310.17419 (2023)"},{"key":"11_CR5","unstructured":"Chen, L., Chen, J., Goldstein, T., Huang, H., Zhou, T.: Instructzero: Efficient instruction optimization for black-box large language models. arXiv preprint arXiv:2306.03082 (2023)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Coccomini, D.A., Esuli, A., Falchi, F., Gennaro, C., Amato, G.: Detecting images generated by diffusers. arXiv preprint arXiv:2303.05275 (2023)","DOI":"10.7717\/peerj-cs.2127"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Corvi, R., Cozzolino, D., Zingarini, G., Poggi, G., Nagano, K., Verdoliva, L.: On the detection of synthetic images generated by diffusion models. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095167"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Cozzolino, D., Poggi, G., Corvi, R., Nie\u00dfner, M., Verdoliva, L.: Raising the bar of ai-generated image detection with clip. arXiv preprint arXiv:2312.00195 (2023)","DOI":"10.1109\/CVPRW63382.2024.00439"},{"key":"11_CR9","unstructured":"Dai, W., Li, J., Li, D., Tiong, A., Zhao, J., Wang, W., Li, B., Fung, P., Hoi, S.: Instructblip: Towards general-purpose vision-language models with instruction tuning. arxiv 2023. arXiv preprint arXiv:2305.065002 (2023)"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"11_CR11","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. Advances in neural information processing systems 27 (2014)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Guarnera, L., Giudice, O., Battiato, S.: Level up the deepfake detection: a method to effectively discriminate images generated by gan architectures and diffusion models. arXiv preprint arXiv:2303.00608 (2023)","DOI":"10.1007\/978-3-031-66431-1_43"},{"key":"11_CR13","unstructured":"He, X., Shen, X., Chen, Z., Backes, M., Zhang, Y.: Mgtbench: Benchmarking machine-generated text detection. arXiv preprint arXiv:2303.14822 (2023)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Ju, Y., Jia, S., Cai, J., Guan, H., Lyu, S.: Glff: Global and local feature fusion for ai-synthesized image detection. IEEE Transactions on Multimedia (2023)","DOI":"10.1109\/TMM.2023.3313503"},{"key":"11_CR15","unstructured":"Keita, M., Hamidouche, W., Bougueffa\u00a0Eutamene, H., Hadid, A., Taleb-Ahmed, A.: Bi-lora: A vision-language approach for synthetic image detection. ArXiv (2024)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"11_CR17","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"11_CR18","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"11_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102103","volume":"103","author":"H Liz-L\u00f3pez","year":"2024","unstructured":"Liz-L\u00f3pez, H., Keita, M., Taleb-Ahmed, A., Hadid, A., Huertas-Tato, J., Camacho, D.: Generation and detection of manipulated multimodal audiovisual content: Advances, trends and open challenges. Information Fusion 103, 102103 (2024)","journal-title":"Information Fusion"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Lorenz, P., Durall, R., Keuper, J.: Detecting images generated by deep diffusion models using their local intrinsic dimensionality. preprint arXiv:2307.02347 (2023)","DOI":"10.1109\/ICCVW60793.2023.00051"},{"key":"11_CR21","unstructured":"Ma, R., Duan, J., Kong, F., Shi, X., Xu, K.: Exposing the fake: Effective diffusion-generated images detection. arXiv preprint arXiv:2307.06272 (2023)"},{"key":"11_CR22","first-page":"35087","volume":"35","author":"Y Ming","year":"2022","unstructured":"Ming, Y., Cai, Z., Gu, J., Sun, Y., Li, W., Li, Y.: Delving into out-of-distribution detection with vision-language representations. Adv. Neural. Inf. Process. Syst. 35, 35087\u201335102 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR23","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., Chen, M.: Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"11_CR24","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. ArXiv:2204.061251(2), 3 (2022)"},{"key":"11_CR25","unstructured":"Ricker, J., Damm, S., Holz, T., Fischer, A.: Towards the detection of diffusion model deepfakes. arXiv preprint arXiv:2210.14571 (2022)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"11_CR27","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E.L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Sha, Z., Li, Z., Yu, N., Zhang, Y.: De-fake: Detection and attribution of fake images generated by text-to-image diffusion models. preprint arXiv:2210.06998 (2022)","DOI":"10.1145\/3576915.3616588"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Sinitsa, S., Fried, O.: Deep image fingerprint: Accurate and low budget synthetic image detector. arXiv preprint arXiv:2303.10762 (2023)","DOI":"10.1109\/WACV57701.2024.00402"},{"key":"11_CR30","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR 2011. pp. 1521\u20131528. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Wang, S.Y., Efros, A.A., Zhu, J.Y., Zhang, R.: Evaluating data attribution for text-to-image models. arXiv preprint arXiv:2306.09345 (2023)","DOI":"10.1109\/ICCV51070.2023.00661"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bao, J., Zhou, W., Wang, W., Hu, H., Chen, H., Li, H.: Dire for diffusion-generated image detection. arXiv preprint arXiv:2303.09295 (2023)","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"11_CR34","unstructured":"Wu, H., Zhou, J., Zhang, S.: Generalizable synthetic image detection via language-guided contrastive learning. arXiv preprint arXiv:2305.13800 (2023)"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Xi, Z., Huang, W., Wei, K., Luo, W., Zheng, P.: Ai-generated image detection using a cross-attention enhanced dual-stream network. ArXiv:2306.07005 (2023)","DOI":"10.1109\/APSIPAASC58517.2023.10317126"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, R., Zhang, W., Fang, R., Gao, P., Li, K., Dai, J., Qiao, Y., Li, H.: Tip-adapter: Training-free adaption of clip for few-shot classification. In: European Conference on Computer Vision. pp. 493\u2013510. Springer (2022)","DOI":"10.1007\/978-3-031-19833-5_29"},{"issue":"9","key":"11_CR37","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Lei, Y., Zhang, B., Liu, L., Liu, Y.: Zegclip: Towards adapting clip for zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11175\u201311185 (2023)","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"11_CR39","unstructured":"Zou, A., Wang, Z., Kolter, J.Z., Fredrikson, M.: Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:2307.15043 (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78305-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T11:14:23Z","timestamp":1733224463000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78305-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031783043","9783031783050"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78305-0_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}