3 papers
cs.SD2026
Probing Speaker Identity Sensitivity in Audio Deepfake Detectors
Daniyal Kabir Dar, Arun Ross
Audio deepfake detectors are trained to distinguish genuine speech from synthetic speech and often perform well on standard benchmarks. Yet the same detector that achieves less tha…
cs.SD2025
Impact of Phonetics on Speaker Identity in Adversarial Voice Attack
Daniyal Kabir Dar, Qiben Yan, Li Xiao +1
Adversarial perturbations in speech pose a serious threat to automatic speech recognition (ASR) and speaker verification by introducing subtle waveform modifications that remain im…
cs.IR2023
How Auditing Methodologies Can Impact Our Understanding of YouTube's Recommendation Systems
Sarmad Chandio, Daniyal Pirwani Dar, Rishab Nithyanand
Data generated by audits of social media websites have formed the basis of our understanding of the biases presented in algorithmic content recommendation systems. As legislators a…