{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T13:17:04Z","timestamp":1781615824754,"version":"3.54.5"},"reference-count":53,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T00:00:00Z","timestamp":1758844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"MOE Industry-University Collaborative Education Project"},{"name":"Philosophy and Social Sciences Research Project of Universities in Jiangsu Province","award":["2024SJYB0345"],"award-info":[{"award-number":["2024SJYB0345"]}]},{"name":"Philosophy and Social Sciences Research Project of Universities in Jiangsu Province","award":["2023SJYB0464"],"award-info":[{"award-number":["2023SJYB0464"]}]},{"name":"Philosophy and Social Sciences Research Project of Universities in Jiangsu Province","award":["2023SJYB0468"],"award-info":[{"award-number":["2023SJYB0468"]}]},{"name":"\u201cCyberspace Security\u201d construction project of key disciplines in Jiangsu Province during the \u201c14th Five-Year Plan\u201d"}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Cryptography"],"abstract":"<jats:p>As deepfake technology matures, its risks in spreading false information and threatening personal and societal security are escalating. Despite significant accuracy improvements in existing detection models, their inherent opacity limits their practical application in high-risk areas such as forensic investigations and news verification. To address this gap in trust, explainability has become a key research focus. This paper provides a systematic review of explainable deepfake detection methods, categorizing them into three main approaches: forensic analysis, which identifies physical or algorithmic manipulation traces; model-centric methods, which enhance transparency through post hoc explanations or pre-designed processes; and multimodal and natural language explanations, which translate results into human-understandable reports. The paper also examines evaluation frameworks, datasets, and current challenges, underscoring the necessity for trustworthy, reliable, and interpretable detection technologies in combating digital misinformation.<\/jats:p>","DOI":"10.3390\/cryptography9040061","type":"journal-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T09:35:49Z","timestamp":1758879349000},"page":"61","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics"],"prefix":"10.3390","volume":"9","author":[{"given":"Hanwei","family":"Qian","sequence":"first","affiliation":[{"name":"Department of Computer Information and Cybersecurity, Jiangsu Police Institute, Nanjing 210031, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingling","family":"Xia","sequence":"additional","affiliation":[{"name":"Department of Computer Information and Cybersecurity, Jiangsu Police Institute, Nanjing 210031, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruihao","family":"Ge","sequence":"additional","affiliation":[{"name":"Department of Computer Information and Cybersecurity, Jiangsu Police Institute, Nanjing 210031, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Fan","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Information and Cybersecurity, Jiangsu Police Institute, Nanjing 210031, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5734-6544","authenticated-orcid":false,"given":"Zhengjun","family":"Jing","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jiangsu University of Technology, Changzhou 213001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.inffus.2020.06.014","article-title":"Deepfakes and beyond: A Survey of face manipulation and fake detection","volume":"64","author":"Tolosana","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"R\u00f6ssler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., and Nie\u00dfner, M. (November, January 27). FaceForensics++: Learning to Detect Manipulated Facial Images. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref_3","unstructured":"Li, Y., and Lyu, S. (2019, January 16\u201320). Exposing DeepFake Videos By Detecting Face Warping Artifacts. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2019, Long Beach, CA, USA."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"118423","DOI":"10.1016\/j.eswa.2022.118423","article-title":"ViXNet: Vision Transformer with Xception Network for deepfakes based video and image forgery detection","volume":"210","author":"Ganguly","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_5","unstructured":"Krishnapuram, B., Shah, M., Smola, A.J., Aggarwal, C.C., Shen, D., and Rastogi, R. (2016, January 13\u201317). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"58:1","DOI":"10.1145\/3699710","article-title":"Deepfake Detection: A Comprehensive Survey from the Reliability Perspective","volume":"57","author":"Wang","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Trinh, L., Tsang, M., Rambhatla, S., and Liu, Y. (2021, January 3\u20138). Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes. Proceedings of the IEEE Winter Conference on Applications of Computer Vision, WACV 2021, Waikoloa, HI, USA.","DOI":"10.1109\/WACV48630.2021.00202"},{"key":"ref_8","unstructured":"Tariq, S., Woo, S.S., Singh, P., Irmalasari, I., Gupta, S., and Gupta, D. (2025). From Prediction to Explanation: Multimodal, Explainable, and Interactive Deepfake Detection Framework for Non-Expert Users. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1109\/TIFS.2006.873602","article-title":"Digital camera identification from sensor pattern noise","volume":"1","author":"Lukas","year":"2006","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2197","DOI":"10.1109\/TIFS.2017.2701335","article-title":"Blind PRNU-based image clustering for source identification","volume":"12","author":"Marra","year":"2017","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2026","DOI":"10.1109\/TIFS.2017.2692683","article-title":"A theoretical framework for estimating false acceptance rate of PRNU-based camera identification","volume":"12","author":"Saito","year":"2017","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_12","first-page":"1","article-title":"DIPPAS: A deep image prior PRNU anonymization scheme","volume":"2022","author":"Picetti","year":"2022","journal-title":"EURASIP J. Inf. Secur."},{"key":"ref_13","unstructured":"Koopman, M., Rodriguez, A.M., and Geradts, Z. (2018, January 29\u201331). Detection of deepfake video manipulation. Proceedings of the 20th Irish Machine Vision and Image Processing Conference (IMVIP), Belfast, UK."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1109\/TIFS.2019.2916364","article-title":"Noiseprint: A CNN-Based Camera Model Fingerprint","volume":"15","author":"Cozzolino","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_15","unstructured":"Cozzolino, D., Poggi, G., and Verdoliva, L. (2019, January 16\u201320). Extracting camera-based fingerprints for video forensics. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Guarnera, L., Giudice, O., and Battiato, S. (2020, January 14\u201319). DeepFake detection by analyzing convolutional traces. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00341"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"165085","DOI":"10.1109\/ACCESS.2020.3023037","article-title":"Fighting deepfake by exposing the convolutional traces on images","volume":"8","author":"Guarnera","year":"2020","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","article-title":"Beyond a gaussian denoiser: Residual learning of deep CNN for image denoising","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_19","first-page":"3336","article-title":"Exposing Deepfake Face Forgeries with Guided Residuals","volume":"25","author":"Guo","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1109\/TCSVT.2022.3204753","article-title":"SNIS: A signal noise separation-based network for post-processed image forgery detection","volume":"33","author":"Chen","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"He, Y., Yu, N., Keuper, M., and Fritz, M. (2021, January 19\u201327). Beyond the spectrum: Detecting deepfakes via re-synthesis. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), Montreal, QC, Canada.","DOI":"10.24963\/ijcai.2021\/349"},{"key":"ref_22","first-page":"1138","article-title":"DeepFake Detection Based on Discrepancies Between Faces and Their Context","volume":"45","author":"Nirkin","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Xu, Y., Raja, K., and Pedersen, M. (2022, January 4\u20138). Supervised Contrastive Learning for Generalizable and Explainable DeepFakes Detection. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), Waikoloa, HI, USA.","DOI":"10.1109\/WACVW54805.2022.00044"},{"key":"ref_24","unstructured":"Sun, K., Yao, T., Chen, S., Ding, S., Li, J., and Ji, R. (March, January 22). Dual Contrastive Learning for General Face Forgery Detection. Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, Online."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Dong, S., Wang, J., Liang, J., Fan, H., and Ji, R. (2022). Explaining deepfake detection by analysing image matching. arXiv.","DOI":"10.1007\/978-3-031-19781-9_2"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Malolan, B., Parekh, A., and Kazi, F. (2020, January 9\u201312). Explainable Deep-Fake Detection Using Visual Interpretability Methods. Proceedings of the International Congress on Information and Communication Technology, London, UK.","DOI":"10.1109\/ICICT50521.2020.00051"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ge, W., Patino, J., Todisco, M., and Evans, N. (July, January 28). Explaining deep learning models for spoofing and deepfake detection with SHapley Additive exPlanations. Proceedings of the Odyssey 2022: The Speaker and Language Recognition Workshop, Beijing, China.","DOI":"10.1109\/ICASSP43922.2022.9747476"},{"key":"ref_29","unstructured":"Parvez, M.A.I. (2024). Explainable Deepfake Video Detection using Convolutional Neural Network and CapsuleNet. arXiv."},{"key":"ref_30","unstructured":"Khan, S. (2022). Explainable Deepfake Detection Using Deep Learning. [Master\u2019s Thesis, NED University of Engineering and Technology]."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Gowrisankar, B., and Thing, V.L. (2023). An adversarial attack approach for eXplainable AI evaluation on deepfake detection models. arXiv.","DOI":"10.1016\/j.cose.2023.103684"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1007\/s00530-023-01248-x","article-title":"A defensive attention mechanism to detect deepfake content across multiple modalities","volume":"30","author":"Asha","year":"2024","journal-title":"Multimed. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"76:1","DOI":"10.1145\/3625231","article-title":"Voice-Face Homogeneity Tells Deepfake","volume":"20","author":"Cheng","year":"2024","journal-title":"ACM Trans. Multim. Comput. Commun. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Qi, H., Guo, Q., Juefei-Xu, F., Li, X., Yang, Y., Zuo, M., Sun, X., Liu, J., Feng, J., and Pu, G. (2020, January 12\u201316). DeepRhythm: Exposing deepfakes with attentional visual heartbeat rhythms. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA.","DOI":"10.1145\/3394171.3413707"},{"key":"ref_35","unstructured":"Pellcier, A.L., Li, Y., and Angelov, P. (2023, January 18\u201324). PUDD: Prototype-based Unified Framework for Deepfake Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA."},{"key":"ref_36","first-page":"239","article-title":"ProtoExplorer: Interpretable Forensic Analysis of Deepfake Videos using Prototype Exploration and Refinement","volume":"23","author":"Pardo","year":"2024","journal-title":"Inf. Visual."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"107950","DOI":"10.1016\/j.patcog.2021.107950","article-title":"PRRNet: Pixel-region relation network for face forgery detection","volume":"116","author":"Shang","year":"2021","journal-title":"Pattern Recognit."},{"key":"ref_38","unstructured":"Soltandoost, E., Plesh, R., Schuckers, S., Peer, P., and \u0160truc, V. (March, January 28). Extracting Local Information from Global Representations for Interpretable Deepfake Detection. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), Tucson, AZ, USA."},{"key":"ref_39","unstructured":"Kong, C., Luo, A., Xia, S., Yu, Y., Li, H., and Kot, A.C. (2024, January 14\u201319). MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection. Proceedings of the 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea."},{"key":"ref_40","unstructured":"Kundu, R., Jia, S., Mohanty, V., Balachandran, A., and Roy-Chowdhury, A.K. (2024). TruthLens: Explainable DeepFake Detection for Face Manipulated and Fully Synthetic Data. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Guo, X., Song, X., Zhang, Y., Liu, X., and Liu, X. (2024). Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector. arXiv.","DOI":"10.1109\/CVPR52734.2025.00019"},{"key":"ref_42","unstructured":"Jia, S., Kundu, R., Balachandran, A., Moreira, D., and Roy-Chowdhury, A.K. (2024). Common Sense Reasoning for Deepfake Detection. arXiv."},{"key":"ref_43","unstructured":"Yan, H., Han, J., Jiang, Y., Yan, B., Liu, J., Wang, X., and Lyu, S. (2024). X2-DFD: A framework for eXplainable and eXtendable Deepfake Detection. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Huang, C., Huang, Z., Chen, Z., Huang, J., Liu, Z., and Tao, D. (2024). SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model. arXiv.","DOI":"10.1109\/CVPR52734.2025.02685"},{"key":"ref_45","unstructured":"Zhang, K., Kong, C., Liu, H., Ding, B., Jiang, X., and Li, H. (2025). Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization. arXiv."},{"key":"ref_46","unstructured":"Narang, A., Gupta, P., Su, L., and Dhall, A. (2025). LayLens: Improving Deepfake Understanding through Simplified Explanations. arXiv."},{"key":"ref_47","unstructured":"Baldassarre, F., Debard, Q., Pontiveros, G.F., and Wijaya, T.K. (2022, January 23\u201327). Quantitative metrics for evaluating explanations of video deepfake detectors. Proceedings of the European Conference on Computer Vision Workshops (ECCVW), Tel Aviv, Israel."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, X., Sun, P., Qi, H., and Lyu, S. (2020, January 13\u201319). Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"ref_49","unstructured":"Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., and Canton-Ferrer, C. (2020). The DeepFake Detection Challenge (DFDC) Dataset. arXiv."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Zi, B., Chang, M., Chen, J., Ma, X., and Jiang, Y. (2020, January 12\u201316). WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA.","DOI":"10.1145\/3394171.3413769"},{"key":"ref_51","unstructured":"Miao, C., Chen, Y., Zhang, Z., Liu, Z., Wang, Z., Wang, S., and Feng, J. (2024). DDL: A Dataset for Interpretable Deepfake Detection and Localization in Real-World Scenarios. arXiv."},{"key":"ref_52","unstructured":"Hondru, V., Hogea, E., Onchis, D.M., and Ionescu, R.T. (2025). ExDDV: A New Dataset for Explainable Deepfake Detection in Video. arXiv."},{"key":"ref_53","unstructured":"Wang, T., Cheng, H., Liu, M., and Kankanhalli, M.S. (2025). FractalForensics: Proactive Deepfake Detection and Localization via Fractal Watermarks. arXiv."}],"container-title":["Cryptography"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2410-387X\/9\/4\/61\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T09:50:50Z","timestamp":1758880250000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2410-387X\/9\/4\/61"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,26]]},"references-count":53,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["cryptography9040061"],"URL":"https:\/\/doi.org\/10.3390\/cryptography9040061","relation":{},"ISSN":["2410-387X"],"issn-type":[{"value":"2410-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,26]]}}}