{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:15:36Z","timestamp":1778152536696,"version":"3.51.4"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:00:00Z","timestamp":1778112000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:00:00Z","timestamp":1778112000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universit\u00e0 degli Studi di Bari Aldo Moro"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The rapid advancement of Deep Learning (DL) techniques has led to the widespread proliferation of DeepFake (DF) images, raising real-world concerns. In this work, DeepDect is proposed and evaluated in a real-world scenario. The platform has been developed using a human-centered approach, integrating insights (requirements) from both common and DF expert users. The platform can detect both face-swapping and generated deepfake faces, which are the most common cases of DF in the current context. Two benchmarks have been conducted to evaluate state-of-the-art DF detection models for face-swap and AI-generated images. The best-performing models (ResNet-50 and Random Forest for face-swapping detection, Capsule Forensics v2, and CNN for AI-generated images) have been integrated into the platform as the detection engine. An Explainable AI (XAI) module has been implemented and integrated into DeepDect to provide visual (Grad-CAM heatmaps) and textual explanations, enhancing interpretability and user trust. A real-world evaluation involving 108 participants was performed to assess DeepDect\u2019s effectiveness compared to human detection. DeepDect has achieved 81% detection accuracy, outperforming human users, underscoring the need for such a tool in real-world applications. These findings have highlighted the importance of accessible, explainable, and high-performing AI solutions, offering a balance between technical robustness and User-Centric Design (UCD).<\/jats:p>","DOI":"10.1007\/s11042-026-21672-1","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T10:54:35Z","timestamp":1778151275000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DeepDect: an explainable AI platform for face swapping and face generation DeepFake detection"],"prefix":"10.1007","volume":"85","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8579-8941","authenticated-orcid":false,"given":"Francesco","family":"Castro","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9974-9414","authenticated-orcid":false,"given":"Vincenzo","family":"Gattulli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9285-2555","authenticated-orcid":false,"given":"Donato","family":"Impedovo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7484-3321","authenticated-orcid":false,"given":"Alessia","family":"Monaco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,7]]},"reference":[{"key":"21672_CR1","doi-asserted-by":"publisher","first-page":"1400024","DOI":"10.3389\/fdata.2024.1400024","volume":"7","author":"E Altuncu","year":"2024","unstructured":"Altuncu E, Franqueira VNL, Li S (2024) Deepfake: definitions, performance metrics and standards, datasets, and a meta-review. Front Big Data 7:1400024. https:\/\/doi.org\/10.3389\/fdata.2024.1400024","journal-title":"Front Big Data"},{"key":"21672_CR2","doi-asserted-by":"publisher","first-page":"429","DOI":"10.55549\/EPSTEM.1371792","volume":"23","author":"SH Al-Khazraji","year":"2023","unstructured":"Al-Khazraji SH, Saleh HH, Khal\u0131d AI, M\u0131shkhal IA (2023) Impact of deepfake technology on social media: detection, misinformation and societal implications. Eurasia Proc Scie Technol Eng Math 23:429\u2013441. https:\/\/doi.org\/10.55549\/EPSTEM.1371792","journal-title":"Eurasia Proc Scie Technol Eng Math"},{"key":"21672_CR3","doi-asserted-by":"publisher","first-page":"104233","DOI":"10.1016\/J.DSP.2023.104233","volume":"143","author":"B Chen","year":"2023","unstructured":"Chen B, Liu X, Xia Z, Zhao G (2023) Privacy-preserving DeepFake face image detection. Digit Signal Process 143:104233. https:\/\/doi.org\/10.1016\/J.DSP.2023.104233","journal-title":"Digit Signal Process"},{"key":"21672_CR4","doi-asserted-by":"publisher","first-page":"39","DOI":"10.22215\/TIMREVIEW\/1282","volume":"9","author":"M Westerlund","year":"2019","unstructured":"Westerlund M (2019) The emergence of deepfake technology: a review. Technol Innov Manage Rev 9:39\u201352. https:\/\/doi.org\/10.22215\/TIMREVIEW\/1282","journal-title":"Technol Innov Manage Rev"},{"key":"21672_CR5","doi-asserted-by":"publisher","unstructured":"Mukta MSH, Ahmad J, Raiaan MAK et al (2023) An investigation of the effectiveness of deepfake models and tools. J Sens Actuator Netw 12:61. https:\/\/doi.org\/10.3390\/JSAN12040061","DOI":"10.3390\/JSAN12040061"},{"key":"21672_CR6","doi-asserted-by":"publisher","first-page":"e42273","DOI":"10.1016\/J.HELIYON.2025.E42273","volume":"11","author":"R Sunil","year":"2025","unstructured":"Sunil R, Mer P, Diwan A et al (2025) Exploring autonomous methods for deepfake detection: a detailed survey on techniques and evaluation. Heliyon 11:e42273. https:\/\/doi.org\/10.1016\/J.HELIYON.2025.E42273","journal-title":"Heliyon"},{"key":"21672_CR7","doi-asserted-by":"publisher","first-page":"117865","DOI":"10.1109\/ACCESS.2023.3324403","volume":"11","author":"S Waseem","year":"2023","unstructured":"Waseem S, Abu Bakar SARS, Ahmed BA et al (2023) DeepFake on face and expression swap: a review. IEEE Access 11:117865\u2013117906. https:\/\/doi.org\/10.1109\/ACCESS.2023.3324403","journal-title":"IEEE Access"},{"key":"21672_CR8","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1016\/J.NEUCOM.2022.09.135","volume":"513","author":"JW Seow","year":"2022","unstructured":"Seow JW, Lim MK, Phan RCW, Liu JK (2022) A comprehensive overview of Deepfake: generation, detection, datasets, and opportunities. Neurocomputing 513:351\u2013371. https:\/\/doi.org\/10.1016\/J.NEUCOM.2022.09.135","journal-title":"Neurocomputing"},{"key":"21672_CR9","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1007\/978-3-030-68821-9_38","volume":"12665 LNCS","author":"R Tolosana","year":"2021","unstructured":"Tolosana R, Romero-Tapiador S, Fierrez J, Vera-Rodriguez R (2021) DeepFakes evolution: analysis of facial regions and fake detection performance. Lecture Notes Comput Sci (including Subser Lecture Notes Artif Intell Lecture Notes Bioinformatics) 12665 LNCS:442\u2013456. https:\/\/doi.org\/10.1007\/978-3-030-68821-9_38","journal-title":"Lecture Notes Comput Sci (including Subser Lecture Notes Artif Intell Lecture Notes Bioinformatics)"},{"key":"21672_CR10","doi-asserted-by":"publisher","first-page":"111299","DOI":"10.1016\/J.PATCOG.2024.111299","volume":"161","author":"L Shi","year":"2025","unstructured":"Shi L, Zhang J, Ji Z et al (2025) Real face foundation representation learning for generalized deepfake detection. Pattern Recognit 161:111299. https:\/\/doi.org\/10.1016\/J.PATCOG.2024.111299","journal-title":"Pattern Recognit"},{"key":"21672_CR11","doi-asserted-by":"publisher","first-page":"129055","DOI":"10.1016\/J.NEUCOM.2024.129055","volume":"618","author":"L Ma","year":"2025","unstructured":"Ma L, Yang P, Xu Y et al (2025) Deep learning technology for face forgery detection: a survey. Neurocomputing 618:129055. https:\/\/doi.org\/10.1016\/J.NEUCOM.2024.129055","journal-title":"Neurocomputing"},{"key":"21672_CR12","unstructured":"Goyal H, Wajid MS, Wajid MA et al (2025) State-of-the-art AI-based learning approaches for deepfake generation and detection, analyzing opportunities, threading through pros, cons, and future prospects"},{"key":"21672_CR13","doi-asserted-by":"publisher","first-page":"16","DOI":"10.37934\/ARASET.47.1.1628","volume":"47","author":"ZN Ashani","year":"2024","unstructured":"Ashani ZN, Ilias ISC, Ng KY et al (2024) Comparative analysis of Deepfake image detection method using VGG16, VGG19 and ResNet50. J Adv Res Appl Sci Eng Technol 47:16\u201328. https:\/\/doi.org\/10.37934\/ARASET.47.1.1628","journal-title":"J Adv Res Appl Sci Eng Technol"},{"key":"21672_CR14","doi-asserted-by":"publisher","unstructured":"Li Y, Zhang C, Sun P et al (2021) DeepFake-o-meter: an open platform for deepFake detection. Proc \u2013 2021 IEEE symp secur priv workshops SPW 2021:277\u2013281. https:\/\/doi.org\/10.1109\/SPW53761.2021.00047","DOI":"10.1109\/SPW53761.2021.00047"},{"key":"21672_CR15","doi-asserted-by":"publisher","unstructured":"Ju Y, Sun C, Jia S et al (2024) DeepFake-O-Meter v2.0: an open platform for deepFake detection. 2024 IEEE 7th international conference on multimedia information processing and retrieval (MIPR). https:\/\/doi.org\/10.1109\/MIPR62202.2024.00075","DOI":"10.1109\/MIPR62202.2024.00075"},{"key":"21672_CR16","doi-asserted-by":"publisher","unstructured":"Mehta V, Gupta P, Subramanian R, Dhall A (2021) FakeBuster: a DeepFakes detection tool for video conferencing scenarios. Int Conf Intell User Interfaces Proc IUI 61\u201363. https:\/\/doi.org\/10.1145\/3397482.3450726","DOI":"10.1145\/3397482.3450726"},{"key":"21672_CR17","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/MSEC.2024.3390555","volume":"22","author":"L Maiano","year":"2024","unstructured":"Maiano L, Benova A, Papa L et al (2024) Human versus machine: a comparative analysis in detecting artificial intelligence-generated images. IEEE Secur Priv 22:77\u201386. https:\/\/doi.org\/10.1109\/MSEC.2024.3390555","journal-title":"IEEE Secur Priv"},{"key":"21672_CR18","doi-asserted-by":"publisher","first-page":"e2110013119","DOI":"10.1073\/PNAS.2110013119\/SUPPL_FILE\/PNAS.2110013119.SAPP.PDF","volume":"119","author":"M Groh","year":"2022","unstructured":"Groh M, Epstein Z, Firestone C, Picard R (2022) Deepfake detection by human crowds, machines, and machine-informed crowds. Proc Natl Acad Sci U S A 119:e2110013119. https:\/\/doi.org\/10.1073\/PNAS.2110013119\/SUPPL_FILE\/PNAS.2110013119.SAPP.PDF","journal-title":"Proc Natl Acad Sci U S A"},{"key":"21672_CR19","first-page":"341","volume":"3486","author":"P Amodio","year":"2023","unstructured":"Amodio P, Antonucci LA, Basile P et al (2023) Human Understanding Capabilities of Symbiotic AI systems in FAIR (Future Artificial Intelligence Research). CEUR Workshop Proc 3486:341\u2013346","journal-title":"CEUR Workshop Proc"},{"key":"21672_CR20","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3233\/IA-240034","volume":"18","author":"A Carnevale","year":"2024","unstructured":"Carnevale A, Lombardi A, Lisi FA (2024) A human-centred approach to symbiotic AI: Questioning the ethical and conceptual foundation. Intelligenza Artificiale 18:9\u201320. https:\/\/doi.org\/10.3233\/IA-240034","journal-title":"Intelligenza Artificiale"},{"key":"21672_CR21","doi-asserted-by":"publisher","first-page":"123732","DOI":"10.1016\/J.ESWA.2024.123732","volume":"249","author":"J Gao","year":"2024","unstructured":"Gao J, Xia Z, Marcialis GL et al (2024) DeepFake detection based on high-frequency enhancement network for highly compressed content. Expert Syst Appl 249:123732. https:\/\/doi.org\/10.1016\/J.ESWA.2024.123732","journal-title":"Expert Syst Appl"},{"key":"21672_CR22","doi-asserted-by":"publisher","unstructured":"Pontorno O, Guarnera L, Battiato S (2024) On the exploitation of DCT-traces in the generative-AI domain. Proc - Int Conf Image Process ICIP 3806\u20133812. https:\/\/doi.org\/10.1109\/ICIP51287.2024.10648013","DOI":"10.1109\/ICIP51287.2024.10648013"},{"key":"21672_CR23","doi-asserted-by":"publisher","unstructured":"Singhal D, Gupta A, Tripathi A, Kothari R (2020) CNN-based multiple manipulation detector using frequency domain features of image residuals. ACM Trans Intell Syst Technol (TIST) 11. https:\/\/doi.org\/10.1145\/3388634","DOI":"10.1145\/3388634"},{"key":"21672_CR24","doi-asserted-by":"publisher","unstructured":"Nguyen HH, Yamagishi J, Echizen I (2022) Capsule-forensics networks for deepfake detection. Adv Comput Vis Pattern Recognit 275\u2013301. https:\/\/doi.org\/10.1007\/978-3-030-87664-7_13\/FIGURES\/7","DOI":"10.1007\/978-3-030-87664-7_13\/FIGURES\/7"},{"key":"21672_CR25","doi-asserted-by":"publisher","unstructured":"Sudharson S, Kokil P, Sasikala D, Swamy PA (2023) Deepfake detection system using a hybrid model. 2023 14th International Conference on Computing Communication and Networking, Technologies ICCCNT 2023. https:\/\/doi.org\/10.1109\/ICCCNT56998.2023.10308279","DOI":"10.1109\/ICCCNT56998.2023.10308279"},{"key":"21672_CR26","doi-asserted-by":"publisher","unstructured":"Nguyen HH, Yamagishi J, Echizen I (2018) Capsule-Forensics: using capsule networks to detect forged images and videos. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2019-May 2307\u20132311. https:\/\/doi.org\/10.1109\/ICASSP.2019.8682602","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"21672_CR27","unstructured":"Hasanaath AA, Luqman H, Katib R, Anwar S (2024) FSBI: Deepfakes detection with frequency enhanced self-blended images. Image Vis Comput"},{"key":"21672_CR28","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761","author":"D Afchar","year":"2018","unstructured":"Afchar D, Nozick V, Yamagishi J, Echizen I (2018) MesoNet: a Compact Facial Video Forgery Detection Network. 10th IEEE Int Workshop Inform Forensics Secur WIFS 2018. https:\/\/doi.org\/10.1109\/WIFS.2018.8630761","journal-title":"10th IEEE Int Workshop Inform Forensics Secur WIFS 2018"},{"key":"21672_CR29","doi-asserted-by":"publisher","unstructured":"Rana MS, Murali B, Sung AH (2021) Deepfake detection using machine learning algorithms. Proc \u2013 2021 10th Int Congress Adv Appl Inf IIAI-AAI 2021:458\u2013463. https:\/\/doi.org\/10.1109\/IIAI-AAI53430.2021.00079","DOI":"10.1109\/IIAI-AAI53430.2021.00079"},{"key":"21672_CR30","unstructured":"Vitalii Mokin (2023) Real and fake face detection. https:\/\/www.kaggle.com\/datasets\/vbmokin\/real-and-fake-face-detection-size-400x400. Accessed 24 Mar 2025"},{"key":"21672_CR31","doi-asserted-by":"crossref","unstructured":"Nguyen HH, Yamagishi J, Echizen I (2019) Use of a capsule network to detect fake images and videos","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"21672_CR32","unstructured":"Frank J, Eisenhofer T, Sch\u00f6nherr L et al (2020) Leveraging frequency analysis for deep fake image recognition. 37th International Conference on Machine Learning, ICML 2020 PartF168147-5:3205\u20133216"},{"key":"21672_CR33","unstructured":"Binh LM, Woo SS (2021) Exploring the asynchronous of the frequency spectra of GAN-generated Facial Images. CEUR Workshop Proc 3084"},{"key":"21672_CR34","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2016","unstructured":"Selvaraju RR, Cogswell M, Das A et al (2016) Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. Int J Comput Vis 128:336\u2013359. https:\/\/doi.org\/10.1007\/s11263-019-01228-7","journal-title":"Int J Comput Vis"},{"key":"21672_CR35","doi-asserted-by":"publisher","first-page":"8261","DOI":"10.1109\/ICASSP.2019.8683164","volume":"2019\u2013May","author":"X Yang","year":"2018","unstructured":"Yang X, Li Y, Lyu S (2018) Exposing Deep Fakes Using Inconsistent Head Poses. ICASSP IEEE Int Conf Acoust Speech Signal Process - Proc 2019\u2013May:8261\u20138265. https:\/\/doi.org\/10.1109\/ICASSP.2019.8683164","journal-title":"ICASSP IEEE Int Conf Acoust Speech Signal Process - Proc"},{"key":"21672_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.fsidi.2024.301795","author":"M Casu","year":"2023","unstructured":"Casu M, Guarnera L, Caponnetto P, Battiato S (2023) GenAI mirage: the impostor bias and the deepfake detection challenge in the era of artificial illusions. Forensic Sci International: Digit Invest. 50: https:\/\/doi.org\/10.1016\/j.fsidi.2024.301795","journal-title":"Forensic Sci International: Digit Invest"},{"key":"21672_CR37","doi-asserted-by":"publisher","unstructured":"Bray SD, Johnson SD, Kleinberg B (2022) Testing human ability to detect deepfake images of human faces. J Cybersecur 9. https:\/\/doi.org\/10.1093\/cybsec\/tyad011","DOI":"10.1093\/cybsec\/tyad011"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21672-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-026-21672-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21672-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T10:54:42Z","timestamp":1778151282000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-026-21672-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,7]]},"references-count":37,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["21672"],"URL":"https:\/\/doi.org\/10.1007\/s11042-026-21672-1","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,7]]},"assertion":[{"value":"28 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors have contributed equally to this work and approved the final manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"500"}}