Towards Understanding the Generative Capability of Adversarially Robust Classifiers
Recently, some works found an interesting phenomenon that adversarially robust classifiers can generate good images comparable to generative models. We investigate this phenomenon from an energy perspective and provide a novel explanation. We reformulate adversarial example generation, adversarial training, and image generation in terms of an energy function. We find that adversarial training contributes to obtaining an energy function that is flat and has low energy around the real data, which is the key for generative capability. Based on our new understanding, we further propose a better adversarial training method, Joint Energy Adversarial Training (JEAT), which can generate high-quality images and achieve new state-of-the-art robustness under a wide range of attacks. The Inception Score of the images (CIFAR-10) generated by JEAT is 8.80, much better than original robust classifiers (7.50).
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance
Denoising diffusion probabilistic models (DDPMs) are a recent family of generative models that achieve state-of-the-art results. In order to obtain class-conditional generation, it was suggested to guide the diffusion pr…
DenoisingImage GenerationYour Classifier Can Do More: Towards Bridging the Gaps in Classification, Robustness, and Generation
Joint Energy-based Models (JEMs), a class of hybrid generative-discriminative models, are well known for their ability to achieve both high classification accuracy and generative capability within a single model. However…
Adversarial RobustnessAdversarially robust segmentation models learn perceptually-aligned gradients
The effects of adversarial training on semantic segmentation networks has not been thoroughly explored. While previous work has shown that adversarially-trained image classifiers can be used to perform image synthesis, w…
Image GenerationImage InpaintingSegmentationSemantic SegmentationScore-Based Generative Classifiers
The tremendous success of generative models in recent years raises the question whether they can also be used to perform classification. Generative models have been used as adversarially robust classifiers on simple data…
ClassificationUnique properties of adversarially trained linear classifiers on Gaussian data
Machine learning models are vulnerable to adversarial perturbations, that when added to an input, can cause high confidence misclassifications. The adversarial learning research community has made remarkable progress in …
BIG-bench Machine LearningBinary ClassificationLearning Theory