论文标题
受对抗训练的神经表征可能已经像相应的生物神经表示一样强大
Adversarially trained neural representations may already be as robust as corresponding biological neural representations
论文作者
论文摘要
灵长类动物的视觉系统是强大感知的黄金标准。因此，人们普遍认为，模仿这些系统基础的神经表现形式将产生具有对手稳定性的人工视觉系统。在这项工作中，我们开发了一种直接对灵长类动物大脑活动进行对抗性视觉攻击的方法。然后，我们利用这种方法来证明上述信念可能不是很好的基础。具体而言，我们报告说，构成灵长类动物视觉系统的生物神经元表现出对对抗性扰动的敏感性，这些扰动与现有（训练有素的）人工神经网络相当。
Visual systems of primates are the gold standard of robust perception. There is thus a general belief that mimicking the neural representations that underlie those systems will yield artificial visual systems that are adversarially robust. In this work, we develop a method for performing adversarial visual attacks directly on primate brain activity. We then leverage this method to demonstrate that the above-mentioned belief might not be well founded. Specifically, we report that the biological neurons that make up visual systems of primates exhibit susceptibility to adversarial perturbations that is comparable in magnitude to existing (robustly trained) artificial neural networks.
