5 papers
Foundation Models are Implicit Deepfake Detectors
Stefan Smeu, Dragos-Alexandru Boldisor, Elisabeta Oneata +1
Pretrained self-supervised representations have emerged as a core component of current deepfake detection methods, yet it remains unclear which of their properties make real and fa…
Anchoring the Unknown: Open-Set Model Attribution via Proxy-Anchor Learning
Cristian-Teodor Neamtu, Serban Mihalache, Stefan Smeu +3
The proliferation of text-to-speech (TTS) systems capable of generating realistic synthetic speech poses growing challenges for audio forensics. While binary deepfake detection has…
Investigating self-supervised representations for audio-visual deepfake detection
Dragos-Alexandru Boldisor, Stefan Smeu, Dan Oneata +1
Self-supervised representations excel at many vision and speech tasks, but their potential for audio-visual deepfake detection remains underexplored. Unlike prior work that uses th…
Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning
Stefan Smeu, Dragos-Alexandru Boldisor, Dan Oneata +1
Good datasets are essential for developing and benchmarking any machine learning system. Their importance is even more extreme for safety critical applications such as deepfake det…
DeCLIP: Decoding CLIP representations for deepfake localization
Stefan Smeu, Elisabeta Oneata, Dan Oneata
Generative models can create entirely new images, but they can also partially modify real images in ways that are undetectable to the human eye. In this paper, we address the chall…