Adversarial examples have shown that albeit highly accurate, models learned by machines, differently from humans, have many weaknesses. However, humans' perception is also fundamentally different from machines, because we do not see the signals which arrive at the retina but a rather complex recreation of them. In this paper, we explore how machines could recreate the input as well as investigate the benefits of such an augmented perception. In this regard, we propose Perceptual Deep Neural Networks ($\varphi$DNN) which also recreate their own input before further processing. The concept is formalized mathematically and two variations of it are developed (one based on inpainting the whole image and the other based on a noisy resized super resolution recreation). Experiments reveal that $\varphi$DNNs and their adversarial training variations can increase the robustness substantially, surpassing both state-of-the-art defenses and pre-processing types of defenses in 100% of the tests. $\varphi$DNNs are shown to scale well to bigger image sizes, keeping a similar high accuracy throughout; while the state-of-the-art worsen up to 35%. Moreover, the recreation process intentionally corrupts the input image. Interestingly, we show by ablation tests that corrupting the input is, although counter-intuitive, beneficial. Thus, $\varphi$DNNs reveal that input recreation has strong benefits for artificial neural networks similar to biological ones, shedding light into the importance of purposely corrupting the input as well as pioneering an area of perception models based on GANs and autoencoders for robust recognition in artificial intelligence.
翻译:Adversari 实例表明,尽管机器所学的模型非常准确,但与人类不同,这些模型有许多弱点。然而,人类的认知也与机器有根本的不同,因为我们看到的信号并没有形成视网膜,而是相当复杂的娱乐。在本文中,我们探索机器如何重新生成输入,并调查这种增强感知的好处。在这方面,我们提议在进一步处理之前,也重新创建自己输入的具有概念性的深层神经网络($\varphie$DNN) 。这个概念在数学上已经正式化,它的两个变异正在形成(一个基于涂抹整个图像,另一个基于振动的超大型解析娱乐娱乐,因为我们没有看到这些信号的信号信号。 $\ varphied$DNNNNN及其对抗性训练变异常能可以大大增强这种坚固性,超过这种增强感知觉的状态的防御和预处理类型。 $varphieDDNNNNNN在进一步处理之前, 其规模被显示为更大的图像规模, 保持类似的较轻的精确的精确度;同时, 州-al-drocial-deal-deal viewal viewal viewal view view view laveal deal redudududustrational lacuducational latings 在我们展示中, viewdal viewm view views viewm views views views view views viewmations viewmations