CAREER: Adversarial Artificial Intelligence for Social Good

人工智能技术的成功导致了它们的广泛部署，机器学习等不确定性推理算法产生了特别高的影响。然而，一个经常被忽视的挑战是许多领域的对抗性，在这些领域中，社会、经济和政治利益可能试图操纵智能系统犯下代价高昂的错误。虽然人工智能在玩国际象棋和扑克等对抗性游戏方面有很长的历史，但这种方法并不适合许多现实世界的情况。拟议研究的目标是基于博弈论、人工智能规划和网络安全的见解，开发一个范围和适用性更广的对抗性人工智能通用框架。拟议研究的一个关键建模见解是，可以将广泛环境中的攻击建模为规划问题，以便可以从根本上将健壮算法视为拦截攻击计划。我们的研究将在Stackelberg博弈框架的基础上，开发新的基础技术，用于不确定条件下的可伸缩计划拦截。建议的技术将利用抽象、状态分解表示和值函数近似的组合。此外，对于考虑完全信息和不完全信息的多阶段拦截问题，还将开发新的可扩展算法，建模为序列随机对策。此外，该研究还将在多防守者和多攻击者拦截游戏中做出新的建模和算法贡献。最后，在更实用的领域，这项研究将在应用对抗性人工智能的进步来建模显示重要对抗性方面的问题方面做出重大的智力贡献，例如隐私保护数据共享、访问控制和审计政策以及疫苗设计。

The success of AI technologies has resulted in their widespread deployment, with algorithms for reasoning under uncertainty, such as machine learning, having a particularly high impact. A challenge that is often ignored, however, is the adversarial nature of many domains, in which social, economic, and political interests may try to manipulate intelligent systems into making costly mistakes. While AI has a long history in playing adversarial games, such as chess and poker, the approaches have not been appropriate for many real-world situations. The goal of the proposed research is to develop a general framework for adversarial AI that is far broader in scope and applicability, building on insights from game theory, AI planning, and cybersecurity.A key modeling insight of the proposed research is that attacks across a broad array of settings can be modeled as planning problems, so that robust algorithms can be fundamentally viewed as interdicting attack plans. Our research will develop new foundational techniques for scalable plan interdiction under uncertainty, building off of the framework of Stackelberg games. Proposed techniques will leverage a combination of abstraction, factored representation of state, and value function approximation. In addition, novel scalable algorithms will be developed for multi-stage interdiction problems, modeled as sequential stochastic games, considering both perfect and imperfect information. Moreover, the research will make novel modeling and algorithmic contributions in multi-defender and multi-attacker interdiction games. Finally, in the more applied arena, the research will make significant intellectual contributions in applying advances in adversarial AI to model problems exhibiting important adversarial aspects, such as privacy-preserving data sharing, access control and audit policies, and vaccine design.