Optimized mixed attention-based bidirectional gradient model for intra-frame video forgery detection

Video forgery has become increasingly prevalent with advanced editing tools, posing serious threats to digital media authenticity. However, existing approaches used for detecting manipulations often faced challenges in handling intra-frame forgeries, decreased generalization, sensitivity to noise, and inadequate selection of key frames, thus leading to a decrease in the overall detection performance. To tackle these issues and to design an effective intra-frame forgery detection system, this research proposes an Optimized Multi-level Mixed Attention-enabled Hybrid Learning-based Bidirectional Gradient (OM²AHL-BiG) Model. The framework leverages the hybrid learning technique to enhance representation of features, Bidirectional Long Short-Term Memory (BiLSTM) for understanding long-range temporal dependencies, and Gradient Boosting Machine (GBM) for precise classification. Additionally, the mixed attention mechanisms allow for refining relevant features, and the Cooperative Search Hunter optimization (CoSH) is designed for hyperparameter tuning in order to improve the detection accuracy. Overall, the OM²AHL-BiG model results in enhanced detection, adaptability to various forgery types, and improved interpretability, making it an effective solution for detecting deepfake and intra-frame video forgeries. The experimental results obtained on the FaceForensics++ dataset showcased an improved performance under 90% of training percentage by yielding an accuracy of 98.62%, precision of 99.2%, sensitivity of 98.04%, specificity of 98.91%, and 98.62% F1 score, surpassing conventional approaches effectively.