Modelling Adversarial Noise for Trustworthy Data Analytics

对抗健壮性是值得信赖的机器学习的核心属性。该项目旨在为机器配备能够模拟对抗性噪声的能力，以防御对抗性攻击。该项目预计将产生人工智能的下一个伟大步骤--大力探索和利用欺骗性数据的潜力。该项目的预期成果包括建立对抗性噪声模型的理论基础，以及在嘈杂和恶劣环境中容纳数据的下一代智能系统。通过应用可信地分析其相应的复杂数据，这将使科学、社会和经济在国内和国际上受益。

Adversarial robustness is a core property of trustworthy machine learning. This project aims to equip machines with the ability to model adversarial noise for defending adversarial attacks. The project expects to produce the next great step for artificial intelligence – the potential to robustly explore and exploit deceptive data. Expected outcomes of this project include theoretical foundations for modelling adversarial noise and the next generation of intelligent systems to accommodate data in a noisy and hostile environment. This should benefit science, society, and the economy nationally and internationally through the applications to trustworthily analyse their corresponding complex data.