{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:10:41Z","timestamp":1742955041636,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":51,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819615247"},{"type":"electronic","value":"9789819615254"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-1525-4_16","type":"book-chapter","created":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T09:28:59Z","timestamp":1739698139000},"page":"291-308","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Outliers are Real: Detecting VLM-Generated Images via\u00a0One-Class Classification"],"prefix":"10.1007","author":[{"given":"Baoping","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3603-6617","authenticated-orcid":false,"given":"Bo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3690-0321","authenticated-orcid":false,"given":"Ming","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,17]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Afchar, D., Nozick, V., Yamagishi, J., Echizen, I.: Mesonet: a compact facial video forgery detection network. In: 2018 IEEE International Workshop on Information Forensics and Security (WIFS), pp.\u00a01\u20137. IEEE (2018)","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"16_CR2","unstructured":"Arnaud58: Landscape pictures (2019). https:\/\/www.kaggle.com\/datasets\/arnaud58\/landscape-pictures. Accessed 23 May 2024"},{"key":"16_CR3","unstructured":"AUTOMATIC1111: Stable diffusion webui (2022). https:\/\/github.com\/AUTOMATIC1111\/stable-diffusion-webui"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Bammey, Q.: Synthbuster: towards detection of diffusion model generated images. IEEE Open J. Signal Process. (2023)","DOI":"10.1109\/OJSP.2023.3337714"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Cho, H., Seol, J., Lee, S.G.: Masked contrastive learning for anomaly detection. arXiv preprint arXiv:2105.08793 (2021)","DOI":"10.24963\/ijcai.2021\/198"},{"key":"16_CR6","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 (CVPR), pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"16_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":"16_CR8","doi-asserted-by":"crossref","unstructured":"Crowson, K., et al.: Vqgan-clip: open domain image generation and editing with natural language guidance. In: European Conference on Computer Vision, pp. 88\u2013105. Springer (2022)","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: Protecting celebrities from deepfake with identity consistency transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9468\u20139478 (2022)","DOI":"10.1109\/CVPR52688.2022.00925"},{"key":"16_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Durall, R., Keuper, M., Keuper, J.: Watch your up-convolution: CNN based generative deep neural networks are failing to reproduce spectral distributions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7890\u20137899 (2020)","DOI":"10.1109\/CVPR42600.2020.00791"},{"key":"16_CR12","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":"16_CR13","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR15","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Jeong, Y., Kim, D., Min, S., Joe, S., Gwon, Y., Choi, J.: Bihpf: bilateral high-pass filters for robust deepfake detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 48\u201357 (2022)","DOI":"10.1109\/WACV51458.2022.00293"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Jeong, Y., Kim, D., Ro, Y., Choi, J.: Frepgan: robust deepfake detection using frequency-level perturbations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 1060\u20131068 (2022)","DOI":"10.1609\/aaai.v36i1.19990"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"16_CR19","unstructured":"Keshtmand, N., Santos-Rodriguez, R., Lawry, J.: Typicality-based point OOD detection with contrastive learning. In: Northern Lights Deep Learning Conference, pp. 120\u2013129. PMLR (2024)"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Khalid, H., Woo, S.S.: Oc-fakedect: classifying deepfakes using one-class variational autoencoder. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 656\u2013657 (2020)","DOI":"10.1109\/CVPRW50498.2020.00336"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., Ye, J.C.: Diffusionclip: text-guided diffusion models for robust image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2426\u20132435 (2022)","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"16_CR22","doi-asserted-by":"publisher","unstructured":"Koliha, N.: AI recognition dataset (2024). https:\/\/doi.org\/10.34740\/KAGGLE\/DSV\/7501337","DOI":"10.34740\/KAGGLE\/DSV\/7501337"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Liu, B., Liu, B., Ding, M., Zhu, T., Yu, X.: Ti2net: temporal identity inconsistency network for deepfake detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 4691\u20134700 (2023)","DOI":"10.1109\/WACV56688.2023.00467"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Tan, Z., Tan, C., Wei, Y., Wang, J., Zhao, Y.: Forgery-aware adaptive transformer for generalizable synthetic image detection. In: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01024"},{"key":"16_CR25","unstructured":"Mirzaei, H., et al.: Fake it till you make it: towards accurate near-distribution novelty detection. arXiv preprint arXiv:2205.14297 (2022)"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Mundra, S., Porcile, G.J.A., Marvaniya, S., Verbus, J.R., Farid, H.: Exposing GAN-generated profile photos from compact embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 884\u2013892 (2023)","DOI":"10.1109\/CVPRW59228.2023.00095"},{"key":"16_CR27","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: International Conference on Machine Learning, pp. 16784\u201316804. PMLR (2022)"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Papa, L., Faiella, L., Corvitto, L., Maiano, L., Amerini, I.: On the use of stable diffusion for creating realistic faces: from generation to detection. In: 2023 11th International Workshop on Biometrics and Forensics (IWBF), pp.\u00a01\u20136. IEEE (2023)","DOI":"10.1109\/IWBF57495.2023.10156981"},{"key":"16_CR29","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"16_CR30","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Reiss, T., Cohen, N., Bergman, L., Hoshen, Y.: Panda: adapting pretrained features for anomaly detection and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2806\u20132814 (2021)","DOI":"10.1109\/CVPR46437.2021.00283"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Reiss, T., Hoshen, Y.: Mean-shifted contrastive loss for anomaly detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2155\u20132162 (2023)","DOI":"10.1609\/aaai.v37i2.25309"},{"key":"16_CR33","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":"16_CR34","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"16_CR35","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":"16_CR36","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"16_CR37","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., 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":"16_CR38","doi-asserted-by":"crossref","unstructured":"Seifi, S., Reino, D.O., Chumerin, N., Aljundi, R.: OOD aware supervised contrastive learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1956\u20131966 (2024)","DOI":"10.1109\/WACV57701.2024.00196"},{"key":"16_CR39","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Tan, C., et al.: Rethinking the up-sampling operations in CNN-based generative network for generalizable deepfake detection (2023)","DOI":"10.1109\/CVPR52733.2024.02657"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: M2TR: multi-modal multi-scale transformers for deepfake detection. In: Proceedings of the 2022 International Conference on Multimedia Retrieval, pp. 615\u2013623 (2022)","DOI":"10.1145\/3512527.3531415"},{"key":"16_CR42","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8695\u20138704 (2020)","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yu, K., Chen, C., Hu, X., Peng, S.: Dynamic graph learning with content-guided spatial-frequency relation reasoning for deepfake detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7278\u20137287 (2023)","DOI":"10.1109\/CVPR52729.2023.00703"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Dire for diffusion-generated image detection. arXiv preprint arXiv:2303.09295 (2023)","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Z.J., Montoya, E., Munechika, D., Yang, H., Hoover, B., Chau, D.H.: Diffusiondb: a large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2210.14896 (2022)","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"16_CR46","unstructured":"Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., Duan, N.: Visual chatgpt: talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671 (2023)"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Yang, T., Huang, Z., Cao, J., Li, L., Li, X.: Deepfake network architecture attribution. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 4662\u20134670 (2022)","DOI":"10.1609\/aaai.v36i4.20391"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"16_CR49","doi-asserted-by":"publisher","first-page":"1335","DOI":"10.1109\/TIFS.2023.3239223","volume":"18","author":"C Zhao","year":"2023","unstructured":"Zhao, C., Wang, C., Hu, G., Chen, H., Liu, C., Tang, J.: ISTVT: interpretable spatial-temporal video transformer for deepfake detection. IEEE Trans. Inf. Forensics Secur. 18, 1335\u20131348 (2023)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"16_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhou, W., Chen, D., Wei, T., Zhang, W., Yu, N.: Multi-attentional deepfake detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2185\u20132194 (2021)","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"16_CR51","unstructured":"Zhu, M., et al.: Genimage: a million-scale benchmark for detecting AI-generated image. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1525-4_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T09:29:56Z","timestamp":1739698196000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1525-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819615247","9789819615254"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1525-4_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"17 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macau","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"30 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ica3pp2024.scimeeting.cn\/en\/web\/index\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}