no code implementations • 1 Feb 2023 • Chen Chen, Dylan Walker, Venkatesh Saligrama
We propose a novel supervised learning approach for political ideology prediction (PIP) that is capable of predicting out-of-distribution inputs.
no code implementations • 31 Jan 2023 • Brandon B. May, N. Joseph Tatro, Dylan Walker, Piyush Kumar, Nathan Shnidman
We propose a novel algorithm, Salient Conditional Diffusion (Sancdifi), a state-of-the-art defense against backdoor attacks.