Learning Generative Deception Strategies in Combinatorial Masking Games

Learning Generative Deception Strategies in Combinatorial Masking Games
复制标题

学习组合掩蔽游戏中的生成欺骗策略

DOI:
10.1007/978-3-030-90370-1_6
复制
发表时间:
2022
期刊:
Conference on Game Theory and Decision Theory for Security
影响因子:
--
通讯作者:
Vorobeychik, Yevgeniy
Vorobeychik, Yevgeniy
中科院分区:
--
文献类型:
--
作者:
Wu, Junlin;Kamhoua, Charles;Kantarcioglu, Murat;Vorobeychik, Yevgeniy

文献摘要

参考文献

相似文献

欺骗是网络防御中的一个重要工具,使防御者能够利用其信息优势来降低成功攻击的可能性。欺骗的一种方式是通过模糊或掩盖一些关于系统如何配置的信息,增加攻击者对其目标的不确定性。我们提出了一种新的博弈论模型,由此产生的防御者-攻击者的相互作用,防御者选择一个子集的属性来屏蔽,而攻击者通过选择一个漏洞来执行。两个参与者的策略都具有复杂信息依赖的组合结构,因此即使表示这些策略也不是微不足道的。首先,我们证明了计算零和防御者-攻击者博弈的平衡的问题可以表示为一个线性规划与系统配置变量和约束的组合数,并开发了一个约束生成方法来解决这个问题。接下来,我们提出了一种新的高度可扩展的方法,通过将两个玩家的策略表示为神经网络来近似求解此类游戏。其关键思想是使用深度神经网络生成器来表示防御者的混合策略,然后使用交替梯度下降上升算法,类似于生成对抗网络的训练。我们的实验,以及案例研究,证明了所提出的方法的有效性。
Deception is a crucial tool in the cyberdefence repertoire, enabling defenders to leverage their informational advantage to reduce the likelihood of successful attacks. One way deception can be employed is through obscuring, or masking, some of the information about how systems are configured, increasing attacker’s uncertainty about their targets. We present a novel game-theoretic model of the resulting defender-attacker interaction, where the defender chooses a subset of attributes to mask, while the attacker responds by choosing an exploit to execute. The strategies of both players have combinatorial structure with complex informational dependencies, and therefore even representing these strategies is not trivial. First, we show that the problem of computing an equilibrium of the resulting zero-sum defender-attacker game can be represented as a linear program with a combinatorial number of system configuration variables and constraints, and develop a constraint generation approach for solving this problem. Next, we present a novel highly scalable approach for approximately solving such games by representing the strategies of both players as neural networks. The key idea is to represent the defender’s mixed strategy using a deep neural network generator, and then using alternating gradient-descent-ascent algorithm, analogous to the training of Generative Adversarial Networks. Our experiments, as well as a case study, demonstrate the efficacy of the proposed approach.
通过攻击图引导攻击者进行欺骗
DOI: 10.1016/s0167-4048(03)00506-6
发表时间: 2003
期刊: Comput. Secur.
影响因子: --
作者:
F. Cohen;D. Koike
通讯作者: D. Koike
DOI: 10.1201/9781420019087.sec2
发表时间: 2001
期刊: Comput. Secur.
影响因子: --
作者:
F. Cohen;Dave Lambert;Charles Preston;Nina Berry;Corbin Stewart;E. Thomas
通讯作者: E. Thomas
DOI: 10.1007/978-3-030-32430-8_15
发表时间: 2019-10
期刊: --
影响因子: --
作者:
Nitin Kamra;Umang Gupta;Kai Wang;Fei Fang;Yan Liu;Milind Tambe
通讯作者: Nitin Kamra;Umang Gupta;Kai Wang;Fei Fang;Yan Liu;Milind Tambe
使用深度学习生成关系 HoneyData
DOI: 10.1007/978-3-030-02110-8_1
发表时间: 2019
期刊: Autonomous Cyber Deception
影响因子: --
作者:
E. Al;Jinpeng Wei;Kevin W. Hamlen;Cliff X. Wang
通讯作者: Cliff X. Wang
半真半假的欺骗
DOI: 10.1609/aaai.v34i06.6570
发表时间: 2020
期刊: Proceedings of the AAAI Conference on Artificial Intelligence
影响因子: --
作者:
Estornell, Andrew;Das, Sanmay;Vorobeychik, Yevgeniy
通讯作者: Vorobeychik, Yevgeniy