PhonemeFake: Redefining Deepfake Realism with Language-Driven Segmental Manipulation and Adaptive Bilevel Detection

Deepfake (DF) attacks pose a growing threat as generative models become increasingly advanced. However, our study reveals that existing DF datasets fail to deceive human perception, unlike real DF attacks that influence public discourse. It highlights the need for more realistic DF attack vectors. We introduce PhonemeFake (PF), a DF attack that manipulates critical speech segments using language reasoning, significantly reducing human perception by up to 42% and benchmark accuracies by up to 94%. We release an easy-to-use PF dataset on HuggingFace and open-source bilevel DF segment detection model that adaptively prioritizes compute on manipulated regions. Our extensive experiments across three known DF datasets reveal that our detection model reduces EER by 91% while achieving up to 90% speed-up, with minimal compute overhead and precise localization beyond existing models as a scalable solution.