{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T17:29:53Z","timestamp":1790011793183,"version":"4.0.1"},"reference-count":44,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deepfakes threaten sensor-based authentication systems, including biometric sensors, surveillance cameras, and IoT edge devices. Unimodal detectors remain vulnerable to modality-specific attacks. We propose a multimodal deepfake detection framework optimized for resource-constrained edge devices, featuring a novel cross-modal attention fusion mechanism with adaptive gating. The architecture combines enhanced Res2Net for audio, temporal 3D CNN with SE attention for video, and bidirectional cross-modal attention with quality-based gates. On our benchmark (5472 audio + 1842 video samples), the fusion model achieves 96.7% accuracy, 96.6% F1-score, 0.988 AUC-ROC, and 3.3% EER. Adversarial testing shows 92.3% accuracy under the Fast Gradient Sign Method (FGSM) attack. The model has a 30.3 MB footprint and runs at 20 FPS on edge hardware. Modality contribution analysis reveals adaptive weighting (72% audio for TTS forgery, 78% video for lip-synced attacks). Cross-dataset evaluation on FakeAVCeleb achieves 92.3% overall accuracy, confirming generalization.<\/jats:p>","DOI":"10.3390\/s26123695","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T02:59:31Z","timestamp":1781146771000},"page":"3695","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Sensors-Driven Multimodal Deepfake Detection: A Cross-Attention Fusion Approach with Adaptive Modality Gating"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8974-0397","authenticated-orcid":false,"given":"Syeda Sitara","family":"Waseem","sequence":"first","affiliation":[{"name":"Department of Computer Science & IT, The Government Sadiq College Women University, Bahawalpur 63100, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5193-7707","authenticated-orcid":false,"given":"Noman","family":"Shabbir","sequence":"additional","affiliation":[{"name":"Department of Electrical Power Engineering & Mechatronics, Tallinn University of Technology, 19086 Tallinn, Estonia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6206-3934","authenticated-orcid":false,"given":"Syed Rizwan","family":"Hassan","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3078-6166","authenticated-orcid":false,"given":"KangYoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"ref_1","first-page":"1251","article-title":"Deepfake voice detection using multi-modal attention networks","volume":"18","author":"Wang","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_2","unstructured":"Yi, J., Wang, C., Tao, J., Zhang, X., Zhang, C.Y., and Zhao, Y. (2023). Audio deepfake detection: A survey. arXiv."},{"key":"ref_3","unstructured":"Khalid, H., Kim, J., and Woo, S.S. (2021). FakeAVCeleb: A novel audio-video multimodal deepfake dataset. arXiv."},{"key":"ref_4","unstructured":"Goodfellow, I.J., Shlens, J., and Szegedy, C. (2015, January 7\u20139). Explaining and harnessing adversarial examples. Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Afchar, D., Nozick, V., Yamagishi, J., and Echizen, I. (2018). MesoNet: A compact facial video forgery detection network. IEEE International Workshop on Information Forensics and Security (WIFS), IEEE.","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., and Nie\u00dfner, M. (2019). FaceForensics++: Learning to detect manipulated facial images. IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref_7","unstructured":"Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., and Ferrer, C.C. (2020). The deepfake detection challenge (DFDC) dataset. arXiv."},{"key":"ref_8","unstructured":"Qian, Y., Yin, G., Sheng, L., Chen, Z., and Shao, J. (2020). F3-Net: Frequency-based face forgery detection network. European Conference on Computer Vision (ECCV), Springer."},{"key":"ref_9","unstructured":"Ciftci, U.A., Demir, I., and Yin, L. (2020). FakeCatcher: Detection of synthetic portrait videos using biological signals. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"101114","DOI":"10.1016\/j.csl.2020.101114","article-title":"ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech","volume":"64","author":"Wang","year":"2020","journal-title":"Ital. Speech Lang."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Jung, J.W., Heo, H.S., Tak, H., Shim, H.J., Chung, J.S., Lee, B.J., Yu, H.J., and Evans, N. (2022). AASIST: Audio anti-spoofing using integrated spectro-temporal graph attention networks. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref_12","unstructured":"Carlini, N., and Wagner, D. (2021). Audio adversarial examples: Targeted attacks on speech-to-text. IEEE Symposium on Security and Privacy, IEEE."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hussain, S., Neekhara, P., Jere, M., Koushanfar, F., and McAuley, J. (2021). Adversarial deepfakes: Evaluating vulnerability of deepfake detectors to adversarial examples. IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/WACV48630.2021.00339"},{"key":"ref_14","unstructured":"Mittal, T., Bhatt, M., and Kohli, P. (2020). Learning from multimodal data for deepfake detection. arXiv."},{"key":"ref_15","unstructured":"Liu, P., Tao, Q., and Zhou, J.T. (2024). Evolving from single-modal to multi-modal facial deepfake detection: Progress and challenges. arXiv."},{"key":"ref_16","unstructured":"Wang, Z., Liu, H., and Chen, J. (2024). AVT2-DWF: Audio-visual dual transformers with dynamic weight fusion for deepfake detection. IEEE Transactions on Multimedia, IEEE."},{"key":"ref_17","unstructured":"Li, X., Zhang, Y., and Wang, Q. (2023). Multimodal graph learning for deepfake detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE."},{"key":"ref_18","first-page":"1968","article-title":"Revealing the truth with ConLLM for detecting multi-modal deepfakes","volume":"2026","author":"Kashyap","year":"2026","journal-title":"Find. Assoc. Comput. Linguist. EACL"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Modak, S., Das, A.K., and Naskar, R. SpecViT: A custom vision-transformer based approach for audio deepfake detection. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 6\u201311 April 2025, IEEE.","DOI":"10.1109\/ICASSP49660.2025.10889022"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Park, C., Muneer, M.S., and Woo, S.S. (2025). Beyond masking: Landmark-based representation learning and knowledge-distillation for audio-visual deepfake detection. Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM), ACM.","DOI":"10.1145\/3746252.3760853"},{"key":"ref_21","first-page":"110","article-title":"Spatiotemporal and behavioral feature-aware model with XceptionCapsule fusion for deepfake detection","volume":"25","author":"Rajeev","year":"2026","journal-title":"Inform. Autom."},{"key":"ref_22","unstructured":"Rana, M.S., and Sung, A.H. (2026). DYMAPIA: A multi-domain framework for detecting AI-based video manipulation. arXiv."},{"key":"ref_23","unstructured":"Hong, S., Wang, X., Zhang, C., Wang, J., Duan, P., and Wang, Y. (2026). AIGC video detection based on the fusion of spatial-frequency-optical flow multimodal features. J. Syst. Eng. Electron., early access."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"4350","DOI":"10.1109\/TPAMI.2025.3646016","article-title":"DSwinIR: Rethinking Window-Based Attention for Image Restoration","volume":"48","author":"Wu","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","article-title":"Res2Net: A new multi-scale backbone architecture","volume":"43","author":"Gao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_26","unstructured":"Liu, Y., Zhang, Y., and Wang, S. (2025). Nes2Net: Nested Res2Net for speech anti-spoofing. arXiv."},{"key":"ref_27","unstructured":"Vishal, P., and Kanmani, S. (2026). Multi-scale transformer approaches for multimodal deepfake detection. IEEE Transactions on Artificial Intelligence, IEEE."},{"key":"ref_28","unstructured":"Ghori, D. (2026). Aletheia: Physics-conditioned localized artifact attention for end-to-end generalizable and robust deepfake video detection. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Fan, X., Chen, L., and Wang, H. (2024). Spatial reconstructed local attention Res2Net with F0 subband for fake speech detection. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1016\/j.neunet.2024.106320"},{"key":"ref_30","unstructured":"Lu, Y., Wang, F., and Zhang, L. (2025). Multimodal hybrid expert network with cross-modal attention for deepfake detection. IEEE Transactions on Information Forensics and Security, IEEE."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Valanarasu, J.M.J., and Patel, V.M. (2022). UNeXt: MLP-based rapid medical image segmentation network. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer.","DOI":"10.1007\/978-3-031-16443-9_3"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Das, A., Viji, K.A., and Sebastian, L. (2022). A survey on deepfake video detection techniques using deep learning. Proceedings of the 2022 Second International Conference on Next Generation Intelligent Systems (ICNGIS), Kottayam, India, 29\u201331 July 2022, IEEE.","DOI":"10.1109\/ICNGIS54955.2022.10079802"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Abhinav, T., Vasantha, S.V., Naidu, N.P.V., Amulya, G., and Srikanth, R. (2025). Real and deepfake image similarity detection using transformers. International Conference on Computer Science and Communication Engineering (ICCSCE), Atlantis Press.","DOI":"10.2991\/978-94-6463-858-5_28"},{"key":"ref_34","first-page":"354","article-title":"A comprehensive deepfake detection framework based on multimodal liveness detection and deep learning integration","volume":"20","author":"Yan","year":"2026","journal-title":"KSII Trans. Internet Inf. Syst."},{"key":"ref_35","unstructured":"Wu, H., Cheng, Y., and Bian, S. (2026). M3D-Net: Multi-modal 3D facial feature reconstruction network for deepfake detection. arXiv."},{"key":"ref_36","unstructured":"(2026, April 01). Deep Voice Deepfake Voice Recognition Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/birdy654\/deep-voice-deepfake-voice-recognition."},{"key":"ref_37","unstructured":"(2026, April 01). Lipreading Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/mohamedbentalb\/lipreading-dataset."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","article-title":"Joint face detection and alignment using multitask cascaded convolutional networks","volume":"23","author":"Zhang","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018). Squeeze-and-excitation networks. IEEE CVPR, IEEE.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_40","unstructured":"Yetmgeta, D. (2025). Identifying Deepfake Images with Artificial Intelligence\u2014Enhanced Convolutional Neural Network. [Master\u2019s Thesis, St. Mary\u2019s University]."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1109\/TASLP.2023.3285283","article-title":"ASVspoof 2021: Towards spoofed and deepfake speech detection in the wild","volume":"31","author":"Liu","year":"2023","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Chung, J.S., and Zisserman, A. (2017). Lip reading in the wild. Proceedings of the Asian Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Delgado, H., Todisco, M., Sahidullah, M., Evans, N., Kinnunen, T., Lee, K.A., and Yamagishi, J. (2018). ASVspoof 2017 version 2.0: Meta-data analysis and baseline enhancements. Proceedings of the Odyssey The Speaker and Language Recognition Workshop, ISCA.","DOI":"10.21437\/Odyssey.2018-42"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Haliassos, A., Vougioukas, K., Petridis, S., and Pantic, M. (2021). Lips don\u2019t lie: A generalisable and robust approach to face forgery detection. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR46437.2021.00500"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3695\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:15:58Z","timestamp":1781583358000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":44,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26123695"],"URL":"https:\/\/doi.org\/10.3390\/s26123695","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]}}}