At this year’s International Conference on Learning Representations (ICLR), a group of researchers from the University of Maryland presented an attack technique meant to slow down deep learning models that have been optimized for fast and sensitive operations.
Share this post
Security must be baked into machine learning…
Share this post
At this year’s International Conference on Learning Representations (ICLR), a group of researchers from the University of Maryland presented an attack technique meant to slow down deep learning models that have been optimized for fast and sensitive operations.