CAREER: Adversarial Artificial Intelligence for Social Good

职业：对抗性人工智能造福社会

基本信息

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

项目摘要

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了广泛的部署，并具有在不确定性下进行推理的算法，例如机器学习，具有特别很高的影响。然而，经常被忽略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有昂贵的错误。尽管AI在玩对抗性游戏（例如国际象棋和扑克）方面拥有悠久的历史，但这些方法并不适合许多现实世界中的情况。拟议的研究的目的是为对抗性AI开发一个通用框架，该框架在范围和适用性上更广泛，基于游戏理论，AI计划和网络安全的见解。对拟议研究的关键建模是，跨越一系列设置的攻击可以作为计划的问题建模，因此可以在攻击方面进行攻击，从而使Algoriths构成攻击性的攻击。我们的研究将在不确定性下开发新的基础技术，用于基于Stackelberg Games的框架。提出的技术将利用抽象，状态表示和价值函数近似的组合。此外，考虑到完美和不完美的信息，将开发出新的可扩展算法，用于多阶段的拦截问题，以顺序随机游戏为模型。此外，这项研究将在多人和多攻击者拦截游戏中做出新颖的建模和算法贡献。最后，在更应用的领域中，该研究将在应用对抗性AI的进步方面做出重大智力贡献，以模拟展示重要的对抗方面的问题，例如保护隐私的数据共享，访问控制和审计政策以及疫苗设计。

项目成果

期刊论文数量（14）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Adversarial Regression with Multiple Learners

多个学习者的对抗性回归

DOI：
发表时间：
2018
期刊：
International Conference on Machine Learning
影响因子：
0
作者：
Tong, Liang;Yu, Sixie;Alfeld, Scott;Vorobeychik, Yevgeniy
通讯作者：
Vorobeychik, Yevgeniy

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

DOI：
发表时间：
2018
期刊：
International Conference on Data Engineering
影响因子：
0
作者：
Yan, Chao;Li, Bo;Vorobeychik, Yevgeniy;Laszka, Aron;Fabbri, Daniel;Malin, Bradley
通讯作者：
Malin, Bradley

Adversarial task assignment

对抗性任务分配

DOI：
发表时间：
2018
期刊：
International Joint Conference on Artificial Intelligence
影响因子：
0
作者：
Hajaj, C;Vorobeychik, Y
通讯作者：
Vorobeychik, Y

Adversarial Regression for Detecting Attacks in Cyber-Physical Systems

DOI：
10.24963/ijcai.2018/524
发表时间：
2018-04
期刊：
影响因子：
0
作者：
Amin Ghafouri;Yevgeniy Vorobeychik;X. Koutsoukos
通讯作者：
Amin Ghafouri;Yevgeniy Vorobeychik;X. Koutsoukos

Robust Linear Regression Against Training Data Poisoning

DOI：
10.1145/3128572.3140447
发表时间：
2017-11
期刊：
Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security
影响因子：
0
作者：
Chang Liu;Bo Li;Yevgeniy Vorobeychik;Alina Oprea
通讯作者：
Chang Liu;Bo Li;Yevgeniy Vorobeychik;Alina Oprea