Floods are among the most destructive natural disasters, causing severe damage to human lives, infrastructure, agriculture, and the economy. Accurate and timely flood forecasting is essential for effective disaster preparedness and mitigation. This paper presents a PrivacyAware Federated Deep Learning Framework for Intelligent Flood Forecasting and Water Level Prediction, which combines Federated Learning (FL) with a Feedforward Neural Network (FFNN) to deliver secure and accurate predictions without sharing raw data among participating stations. The proposed framework enables multiple regional nodes to train local models independently while transmitting only model parameters to a central server for global aggregation, thereby preserving data privacy and reducing communication overhead. The aggregated model identifies flood-prone regions and predicts future water levels using hydrological and meteorological parameters. Experimental evaluation demonstrates that the proposed framework achieves high prediction accuracy with low prediction error while ensuring secure, decentralized learning. The proposed system provides a reliable and scalable solution for intelligent flood forecasting and early warning applications.
S. Shivani, Sk.Mahammadunnisa· American Journal of AI Cyber...· 0 citations
Generative AI advancements are rapidly producing highly realistic deepfake videos, which raises major concerns for digital authenticity and security. This paper presents a comparative analysis of representative spatial, temporal, and hybrid deepfake detection architectures. Selected representative models include a lightweight MobileNetV2 + TinyViT hybrid approach; 2D Xception-based spatial model; 3D temporal video model; and the Knowledge-Guided Temporal Transformer (KGTT). Experimental results suggest that hybrid architectures provide the most balanced trade-off among the evaluated models, providing the best compromise between accuracy and computational efficiency. The KGTT model achieved frame-level accuracy exceeding 95%, while the MobileNetV2 + TinyViT hybrid achieved 80.46% accuracy with improved computational efficiency. Further, purely temporal models depend on large-scale, balanced datasets. Collectively, the findings show that integrating complementary feature domains is critical for developing robust and generalizable deepfake detection methods. This study provides a greater under-standing of the strengths and weaknesses of current approaches to deepfake detection, along with insights into promising areas for future research.
Varadharajan Govind, S. Shivani, S. S et al.· 2026 4th International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
