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).

翻译：最近,一些作品发现一个有趣的现象,即对抗性强的分类师能够产生与基因模型相仿的好图像。我们从能源角度对这一现象进行调查,并提供新的解释。我们重新配置对抗性实例生成、对抗性培训和以能源功能为基准的图像生成。我们发现对抗性培训有助于获得一个平坦的能源功能,在真实数据周围的能量较低,而真实数据是基因变异能力的关键。根据我们的新理解,我们进一步建议一种更好的对抗性培训方法,即联合能源反向培训(JEAT),它可以产生高质量的图像,在广泛的攻击中实现新的先进强力。对JEAT产生的图像的感知分数(CIFAR-10)是8.80,比原始强健的分类师(7.50)要好得多。