Image Synthesis with a Single (Robust) Classifier

by   Shibani Santurkar, et al.

We show that the basic classification framework alone can be used to tackle some of the most challenging tasks in image synthesis. In contrast to other state-of-the-art approaches, the toolkit we develop is rather minimal: it uses a single, off-the-shelf classifier for all these tasks. The crux of our approach is that we train this classifier to be adversarially robust. It turns out that adversarial robustness is precisely what we need to directly manipulate salient features of the input. Overall, our findings demonstrate the utility of robustness in the broader machine learning context. Code and models for our experiments can be found at


Computer Vision with a Single (Robust) Classifier

We show that the basic classification framework alone can be used to tac...

Robust Certification for Laplace Learning on Geometric Graphs

Graph Laplacian (GL)-based semi-supervised learning is one of the most u...

MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier

We offer a method for one-shot image synthesis that allows controlling m...

Introspective Classifier Learning: Empower Generatively

In this paper we propose introspective classifier learning (ICL) that em...

Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications

Large-scale pre-trained language models have shown outstanding performan...

On the Benefits of Attributional Robustness

Interpretability is an emerging area of research in trustworthy machine ...

Planting Undetectable Backdoors in Machine Learning Models

Given the computational cost and technical expertise required to train m...

Code Repositories


Notebooks for reproducing the paper "Computer Vision with a Single (Robust) Classifier"

view repo

Please sign up or login with your details

Forgot password? Click here to reset