184 citations · 1k across the 30 of their papers we have counts for
3 papers · 1 filter
On Regularization and Inference with Label Constraints
Kaifu Wang, Hangfeng He, Tin D. Nguyen +2
Prior knowledge and symbolic rules in machine learning are often expressed in the form of label constraints, especially in structured prediction problems. In this work, we compare…
Safety and Fairness for Content Moderation in Generative Models
Susan Hao, Piyush Kumar, Sarah Laszlo +3
With significant advances in generative AI, new technologies are rapidly being deployed with generative components. Generative models are typically trained on large datasets, resul…
Salient Conditional Diffusion for Defending Against Backdoor Attacks
Brandon B. May, N. Joseph Tatro, Dylan Walker +2
We propose a novel algorithm, Salient Conditional Diffusion (Sancdifi), a state-of-the-art defense against backdoor attacks. Sancdifi uses a denoising diffusion probabilistic model…