Adversarial examples are theorized to exist for every type of neural network application. Adversarial examples have been proven to exist in neural networks for visual-spectrum applications and that they are highly transferable between such neural network applications. In this paper, we study the existence of adversarial examples for Infrared neural networks that are applicable to military and surveillance applications. This paper specifically studies the effectiveness of adversarial attacks against neural networks trained on simulated Infrared imagery and the effectiveness of adversarial training. Our research demonstrates the effectiveness of adversarial attacks on neural networks trained on Infrared imagery, something that hasn’t been shown in prior works. Our research shows that an increase in accuracy was shown in both adversarial and unperturbed Infrared images after adversarial training. Adversarial training optimized for the $L_{\infty }$ norm leads to an increase in performance against both adversarial and non-adversarial targets.

中文翻译：

---

用于监视应用的红外示例对抗机器学习的研究

理论上，对抗示例适用于每种类型的神经网络应用。对抗性示例已被证明存在于用于视觉频谱应用的神经网络中，并且它们在此类神经网络应用之间具有很高的可转移性。在本文中，我们研究了适用于军事和监视应用的红外神经网络对抗性示例的存在。本文专门研究了在模拟红外图像上训练的针对神经网络的对抗攻击的有效性以及对抗训练的有效性。我们的研究证明了对抗攻击对以红外图像训练的神经网络的有效性，这在以前的工作中并未得到证明。我们的研究表明，经过对抗训练后，在对抗图像和不受干扰的红外图像中准确性都得到了提高。针对性训练进行了优化${\mathrm{大号}}_{\infty }$ 规范可以提高对抗目标和非对抗目标的绩效。