Search Results for author:
Found 3 papers, 3 papers with code
Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack
Backdoor poisoning attacks pose a well-known risk to neural networks.
Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units
We introduce DISSC, a novel, lightweight method that converts the rhythm, pitch contour and timbre of a recording to a target speaker in a textless manner.
A Universal Adversarial Policy for Text Classifiers
We achieve this by learning a single search policy over a predefined set of semantics preserving text alterations, on many texts.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
