4 papers
De-Fake: Style based Anomaly Deepfake Detection
Sudev Kumar Padhi, Harshit Kumar, Umesh Kashyap +1
Detecting deepfakes involving face-swaps presents a significant challenge, particularly in real-world scenarios where anyone can perform face-swapping with freely available tools a…
Attack GAN (AGAN ): A new Security Evaluation Tool for Perceptual Encryption
Umesh Kashyap, Sudev Kumar Padhi, Sk. Subidh Ali
Training state-of-the-art (SOTA) deep learning models requires a large amount of data. The visual information present in the training data can be misused, which creates a huge priv…
DLOVE: A new Security Evaluation Tool for Deep Learning Based Watermarking Techniques
Sudev Kumar Padhi, Sk. Subidh Ali
Recent developments in Deep Neural Network (DNN) based watermarking techniques have shown remarkable performance. The state-of-the-art DNN-based techniques not only surpass the rob…
Generalized Deepfake Attribution
Sowdagar Mahammad Shahid, Sudev Kumar Padhi, Umesh Kashyap +1
The landscape of fake media creation changed with the introduction of Generative Adversarial Networks (GAN s). Fake media creation has been on the rise with the rapid advances in g…