A hybrid attention-based spatio-temporal model for deepfake video detection.

Deep fake technology has emerged as a pressing global issue, enabling the creation of highly realistic fake videos with severe implications for misinformation, privacy breachesand digital security. The widespread misuse of deep fakes in areas like political propaganda, financial fraud and personal defamation underscores the urgent need for effective detection mechanisms. This paper proposes an Illusion Interception Tool, a robust deep fake detection system, as a novel approach towards the deception of Deep Fake Videos. Though we have some existing solutions for the same, they often focus solely on spatial or temporal inconsistencies and limit their effectiveness against sophisticated forgeries. This paper addresses these gaps with a hybrid framework that combines ResNeXt convolutional neural networks (CNNs) for detailed spatial analysis and long short-term memory (LSTM) networks for capturing temporal dynamics with soft attention. This novel approach effectively identifies both pixel-level artifacts and frame-wise inconsistencies by achieving significant improvements in accuracy and robustness. Thus, by evaluating benchmark datasets such as Face Forensics++ and Celeb-DF here, the present method outperforms existing techniques and achieves up to 94.8% accuracy. Ablation studies confirm the complementary nature of spatial and temporal analysis and our method generalizes well to unseen data.