Development and Explainable Validation of a Multimodal Deep fake and Cyberbullying Detection System: Sift Sentinel

This paper presented Sift Sentinel, a unified system for deep fake and cyberbullying detection that integrates explainable AI and automated report generation. Through comprehensive experiments on diverse datasets, we demonstrated that the system achieves 96.8% accuracy in deep fake detection and 94.2% accuracy in cyberbullying detection, substantially outperforming existing approaches. The integration of multiple XAI techniques (SHAP, LIME, attention mechanisms, Grad-CAM, and integrated gradients) provides transparent, interpretable explanations that enhance trust and enable effective human oversight. The unified architecture offers practical advantages beyond performance improvements. By consolidating two critical detection tasks into a single system, Sift Sentinel reduces operational complexity, development costs, and resource requirements. The automated report generation capability, powered by large language models, creates comprehensive analyses accessible to diverse stakeholders, from technical teams to legal professionals and educators.

1.         X. Liu, Y. Yu, X. Li and Y. Zhao, "MCL: Multimodal Contrastive Learning for Deep Fake Detection," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 4, pp. 2803-2813, April 2024, doi: 10.1109/TCSVT.2023.3312738. 2.         B. A. H. Murshed, J. Abawajy, S. Mallappa, M. A. N. Saif and H. D. E. Al-Ariki, "DEA-RNN: A Hybrid Deep Learning Approach for Cyberbullying Detection in Twitter Social Media Platform," in IEEE Access, vol. 10, pp. 25857-25871, 2022, doi: 10.1109/ACCESS.2022.3153675. 3.         R. Mubarak, T. Alsboui, O. Alshaikh, I. Inuwa-Dutse, S. Khan and S. Parkinson, "A Survey on the Detection and Impacts of Deepfakes in Visual, Audio, and Textual Formats," in IEEE Access, vol. 11, pp. 144497-144529,            2023,     doi: 10.1109/ACCESS.2023.3344653. 4.         Y. Yu, X. Liu, R. Ni, S. Yang, Y. Zhao and A. C. Kot, "PVASS-MDD: Predictive Visual-Audio Alignment Self-Supervision for Multimodal Deep Fake Detection," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 8, pp. 6926-6936, Aug.       2024,     doi: 10.1109/TCSVT.2023.3309899. 5.         F. Khalid, A. Javed, K. M. Malik and A. Irtaza, "ExplaNET: A Descriptive Framework for Detecting Deepfakes with Interpretable Prototypes," in IEEE Transactions on Biometrics, Behaviour, and Identity Science, vol. 6, no. 4, pp. 486-497, Oct. 2024, doi: 10.1109/TBIOM.2024.3407650. 6.         J. Zhang, K. Cheng, G. Sovernigo and X. Lin, "A Heterogeneous Feature Ensemble Learning based Deep Fake Detection Method," ICC 2022 - IEEE International Conference on Communications, Seoul, Korea, Republic of, 2022, pp. 2084-2089, doi: 10.1109/ICC45855.2022.9838630. 7.         S. Jia, X. Li and S. Lyu, "Model Attribution of Face-Swap Deep fake Videos," 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France, 2022, pp. 2356-2360, doi: 10.1109/ICIP46576.2022.9897972. 8.         J. Choi, T. Kim and J. Choi, "ID-Flow: Leveraging Voice Identity for Generalizing Audio Deep fake Detection," 2025 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, 2025,  pp.  1-5,                    doi: 10.1109/ICCE63647.2025.10929900. 9.         M. S. Rana, M. N. Nobi, B. Murali and A. H. Sung, "Deep fake Detection: A Systematic Literature Review," in IEEE Access, vol. 10, pp. 25494-25513, 2022, doi: 10.1109/ACCESS.2022.3154404. 10.     Malik, M. Kuribayashi, S. M. Abdullahi and A. N. Khan, "DeepFake Detection for Human Face Images and Videos: A Survey," in IEEE Access, vol. 10, pp. 18757-18775,      2022,     doi: 10.1109/ACCESS.2022.3151186.