Defending Artificial Intelligence against deception attacks

人工智能依靠深度学习作为其核心驱动工具。然而，深度学习很容易受到恶意攻击，这些攻击可以操纵数据或在深度模型中嵌入特洛伊木马，以获得对人工智能系统的完全控制。该项目旨在通过全面解决人工智能系统易受攻击的问题，确保其用于防御应用的安全。这些结果很可能使恶意攻击的检测能够深入学习，识别攻击源，估计攻击者的能力，并清理模型和数据的恶性影响。这将显著提高我们理解和防御人工智能漏洞的能力，从而使国防和现代技术都受益。

Artificial Intelligence relies on deep learning as its central driving tool. However, deep learning is vulnerable to malicious attacks that can manipulate data or embed Trojans in the deep models to gain full control over the AI system. This project aims to secure AI systems for defense applications by comprehensively addressing its vulnerabilities to attacks. The outcomes are likely to enable the detection of malicious attacks on deep learning, identification of the attack sources, estimation of attackers' capabilities and cleansing of the model and data of the malignant effects. This will significantly advance our capability to understand and defend against AI vulnerabilities, thereby benefiting defense and modern technologies alike.