Rashmi Ashtagi

Attention consistency for robust deepfake detection : An informationtheoretic perspective

Swati Jadhav, Sagar Mohite, Vaishali Rajput, Rashmi Ashtagi, Anusha Pai, Santushti Betgeri

In this paper: The increasing realism of Deepfake media generated by modern models poses significant risks to digital trust and forensics. Although Vision Transformer-based detectors outperform Convolutional Methods...