CAREER: Adversarial Artificial Intelligence for Social Good

职业：对抗性人工智能造福社会

• 批准号: 1649972
• 负责人: Yevgeniy Vorobeychik
• 金额: $ 51.86万
• 依托单位: Vanderbilt University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-03-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1649972&HistoricalAwards=false
• 关键词: CAREER; Adversarial; Artificial; Intelligence; Social

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.

人工智能技术的成功导致其广泛部署，其中机器学习等在不确定性下进行推理的算法具有特别高的影响力。 然而，一个经常被忽视的挑战是许多领域的对抗性，其中社会、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着悠久的历史，但这些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泛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，跨领域的攻击广泛的设置可以建模为规划问题，因此稳健的算法从根本上可以被视为拦截攻击计划。 我们的研究将在 Stackelberg 博弈框架的基础上，开发新的基础技术，用于不确定性下的可扩展计划拦截。所提出的技术将利用抽象、状态分解表示和值函数近似的组合。 此外，还将针对多阶段拦截问题开发新颖的可扩展算法，将其建模为顺序随机博弈，同时考虑完美和不完美的信息。此外，该研究将为多防御者和多攻击者拦截游戏做出新颖的建模和算法贡献。 最后，在更多的应用领域，该研究将在应用对抗性人工智能的进步来对表现出重要对抗性方面的问题进行建模方面做出重大的智力贡献，例如隐私保护数据共享、访问控制和审计策略以及疫苗设计。

项目成果

Get Your Workload in Order: Game Theoretic Prioritization of Database Auditing

让您的工作负载井井有条：数据库审计的博弈论优先级

• 发表时间: 2018-01
• 期刊: International Conference on Data Engineering
• 作者: Yan, Chao;Li, Bo;Vorobeychik, Yevgeniy;Laszka, Aron;Fabbri, Daniel;Malin, Bradley
• 通讯作者: Malin, Bradley

Evasion-Robust Classification on Binary Domains

二进制域上的规避鲁棒分类

• DOI: 10.1145/3186282
• 发表时间: 2018-07
• 期刊: ACM Transactions on Knowledge Discovery from Data
• 影响因子: 3.6
• 作者: Li, Bo;Vorobeychik, Yevgeniy
• 通讯作者: Vorobeychik, Yevgeniy

Adversarial task assignment

对抗性任务分配

• 发表时间: 2018-01
• 期刊: International Joint Conference on Artificial Intelligence
• 作者: Hajaj, C;Vorobeychik, Y
• 通讯作者: Vorobeychik, Y

Integrating linear optimization with structural modeling to increase HIV neutralization breadth

将线性优化与结构建模相结合，以增加 HIV 中和广度

• 发表时间: 2018-01
• 期刊: PLOS computational biology
• 作者: Sevy, Alexander;Panda, Swetasudha;Crowe, James E;Meiler, Jens;Vorobeychik, Yevgeniy
• 通讯作者: Vorobeychik, Yevgeniy

Deceiving Cyber Adversaries: A Game Theoretic Approach

欺骗网络对手：博弈论方法

• 发表时间: 2018-07-09
• 作者: Aaron Schlenker;Omkar Thakoor;Haifeng Xu;Fei Fang;Milind Tambe;Long Tran;P. Vayanos;Yevgeniy Vorobeychik
• 通讯作者: Yevgeniy Vorobeychik