Game Theory and Machine Learning for Cyber Security最新文献

Continuous Authentication Security Games 连续认证安全游戏

Game Theory and Machine Learning for Cyber Security Pub Date : 2021-09-12 DOI: 10.1002/9781119723950.ch11

Serkan Sarıtaş, Ezzeldin Shereen, H. Sandberg, G. Dán

引用次数: 0

Cyber Autonomy in Software Security: Techniques and Tactics 软件安全中的网络自治:技术与策略

Game Theory and Machine Learning for Cyber Security Pub Date : 2021-09-12 DOI: 10.1002/9781119723950.ch12

Tiffany Bao, Yan Shoshitaishvili

{"title":"Cyber Autonomy in Software Security: Techniques and Tactics","authors":"Tiffany Bao, Yan Shoshitaishvili","doi":"10.1002/9781119723950.ch12","DOIUrl":"https://doi.org/10.1002/9781119723950.ch12","url":null,"abstract":"Software security research traditionally focuses on the development of specific offense and defense techniques on software vulnerabilities. Software security techniques are useful in practice only to the extent they can be leveraged to achieve a goal. Different parties‐individuals, companies, or nations‐implement offensive and defensive techniques as components in holistic systems, and these systems strategically interact with each other.This chapter aims to introduce to the reader cyber autonomy in software security. We will offer a holistic view on this topic by presenting both techniques and tactics in software security. This chapter will introduce the high‐level model of cyber autonomy in software security and explain how techniques and tactics co‐work in software security, discuss current software security techniques (including vulnerability discovery, exploit generation, vulnerability patching, and vulnerability ricochet) and, once the readers have gained familiarity with the background and the context in software security that serves as the prerequisites for building a game theoretical model, will introduce the autonomous computer security game, which is the core of the chapter.","PeriodicalId":332247,"journal":{"name":"Game Theory and Machine Learning for Cyber Security","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131218870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Machine Learning in the Hands of a Malicious Adversary: A Near Future If Not Reality 1 恶意对手手中的机器学习:即使不是现实，也不远的将来

Game Theory and Machine Learning for Cyber Security Pub Date : 2021-09-12 DOI: 10.1002/9781119723950.ch15

Key-whan Chung, Xiao Li, Peicheng Tang, Zeran Zhu, Z. Kalbarczyk, T. Kesavadas, R. Iyer

{"title":"Machine Learning in the Hands of a Malicious Adversary: A Near Future If Not Reality\u0000 1","authors":"Key-whan Chung, Xiao Li, Peicheng Tang, Zeran Zhu, Z. Kalbarczyk, T. Kesavadas, R. Iyer","doi":"10.1002/9781119723950.ch15","DOIUrl":"https://doi.org/10.1002/9781119723950.ch15","url":null,"abstract":"Machine learning and artificial intelligence are being adopted to varying applications for automation and flexibility. Cyber security to be no different, researchers and engineers have been investigating the use of data‐driven technologies to harden the security of cyberinfrastructure and the possibility of attackers exploiting vulnerabilities in such technology (e.g. adversarial machine learning). However, not much work has investigated how attackers might try to take advantage of machine learning and AI technology against us. This chapter discusses the potential advances in targeted attacks through the utilization of machine learning techniques. In this chapter, we introduce a new concept of AI‐driven malware which advances already sophisticated cyber threats (i.e. advanced targeted attacks) that are on the rise. Furthermore, we demonstrate our prototype AI‐driven malware, built on top of a set of statistical learning technologies, on two distinct cyber‐physical systems (i.e. the Raven‐II surgical robot and a building automation system). Our experimental results demonstrate that with the support of AI technology, malware can mimic human attackers in deriving attack payloads that are custom to the target system and in determining the most opportune time to trigger the attack payload so to maximize the chance of success in realizing the malicious intent. No public records report a real threat driven by machine learning models. However, such advanced malware might already exist and simply remain undetected. We hope this chapter motivates further research on advanced offensive technologies, not to favor the adversaries, but to know them and be prepared.","PeriodicalId":332247,"journal":{"name":"Game Theory and Machine Learning for Cyber Security","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133246954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Moving Target Defense Games for Cyber Security: Theory and Applications 网络安全的移动目标防御游戏:理论与应用

Game Theory and Machine Learning for Cyber Security Pub Date : 2021-09-12 DOI: 10.1002/9781119723950.ch10

Abdelrahman Eldosouky, S. Sengupta

引用次数: 3

A Game Theoretic Perspective on Adversarial Machine Learning and Related Cybersecurity Applications 对抗性机器学习及相关网络安全应用的博弈论视角

Game Theory and Machine Learning for Cyber Security Pub Date : 2021-09-12 DOI: 10.1002/9781119723950.ch13

Yan Zhou, Murat Kantarcioglu, B. Xi

{"title":"A Game Theoretic Perspective on Adversarial Machine Learning and Related Cybersecurity Applications","authors":"Yan Zhou, Murat Kantarcioglu, B. Xi","doi":"10.1002/9781119723950.ch13","DOIUrl":"https://doi.org/10.1002/9781119723950.ch13","url":null,"abstract":"In cybersecurity applications where machine learning algorithms are increasingly used to detect vulnerabilities, a somewhat unique challenge arises as exploits targeting machine learning models are constantly devised by the attackers. Traditional machine learning models are no longer robust and reliable when they are under attack. The action and reaction between machine learning systems and the adversary can be modeled as a game between two or more players. Under well‐defined attack models, game theory can provide robustness guarantee for machine learning models that are otherwise vulnerable to application‐time data corruption. We review two cases of game theory‐based machine learning techniques: in one case, players play a zero sum game by following a minimax strategy, while in the other case, players play a sequential game with one player as the leader and the rest as the followers. Experimental results on e‐mail spam and web spam datasets are presented. In the zero sum game, we demonstrate that an adversarial SVM model built upon the minimax strategy is much more resilient to adversarial attacks than standard SVM and one‐class SVM models. We also show that optimal learning strategies derived to counter overly pessimistic attack models can produce unsatisfactory results when the real attacks are much weaker. In the sequential game, we demonstrate that the mixed strategy, allowing a player to randomize over available strategies, is the best solution in general without knowing what types of adversaries machine learning applications are facing in the wild. We also discuss scenarios where players' behavior may derail rational decision making and models that consider such decision risks.","PeriodicalId":332247,"journal":{"name":"Game Theory and Machine Learning for Cyber Security","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122368870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Introduction to Game Theory 博弈论概论

Game Theory and Machine Learning for Cyber Security Pub Date : 2021-09-12 DOI: 10.1002/9781119723950.ch2

Fei Fang, Shutian Liu, Anjon Basak, Quanyan Zhu, Christopher Kiekintveld, C. Kamhoua

引用次数: 1

Evaluating Adaptive Deception Strategies for Cyber Defense with Human Adversaries 评估人类对手网络防御的自适应欺骗策略

Game Theory and Machine Learning for Cyber Security Pub Date : 2021-09-12 DOI: 10.1002/9781119723950.ch5

Palvi Aggarwal, Marcus Gutierrez, Chris Kiekintveld, B. Bosanský, Cleotilde González

{"title":"Evaluating Adaptive Deception Strategies for Cyber Defense with Human Adversaries","authors":"Palvi Aggarwal, Marcus Gutierrez, Chris Kiekintveld, B. Bosanský, Cleotilde González","doi":"10.1002/9781119723950.ch5","DOIUrl":"https://doi.org/10.1002/9781119723950.ch5","url":null,"abstract":"We investigate the effectiveness of various algorithms for defensive cyber‐deception in an adversarial decision‐making task using human experiments. Our combinatorial Multi‐Armed Bandit task represents an abstract version of a realistic problem in cybersecurity: allocating limited resources for defense in a way that an adversary can be most successfully deceived to attack “fake” nodes (i.e., honeypots) instead of the real ones. We propose six algorithms with different degrees of determinism, adaptivity, and customization to the human adversary's actions. We test these algorithms in six separate behavioral studies, where humans are paired against each of the six types of defense. We measure the effectiveness of the algorithms according to how humans learn the defense strategies, which is a reflection of the success of the algorithms in deceiving human adversaries. We find that the adaptivity of the strategy is more important than the expected optimality of the algorithm. Humans learned and took advantage of defense algorithms that are deterministic, nonadaptive, and not customized. At the same time, not all algorithms that were nondeterministic, adaptive, and customized, were effective. The Learning with Linear Rewards (LLR) algorithm, one that was purely adaptive, was the most successful; suggesting that adaptivity is an important feature of defense algorithms. New ways to customize the defense strategies to the adversary's behavior are needed.","PeriodicalId":332247,"journal":{"name":"Game Theory and Machine Learning for Cyber Security","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130276290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Smart Internet Probing: Scanning Using Adaptive Machine Learning 智能互联网探测:使用自适应机器学习进行扫描

Game Theory and Machine Learning for Cyber Security Pub Date : 2021-09-12 DOI: 10.1002/9781119723950.ch21

Armin Sarabi, Kun Jin, Mingyan D. Liu

引用次数: 2

Resource‐Aware Intrusion Response Based on Deep Reinforcement Learning for Software‐Defined Internet‐of‐Battle‐Things 基于深度强化学习的软件定义物联网资源感知入侵响应

Game Theory and Machine Learning for Cyber Security Pub Date : 2021-09-12 DOI: 10.1002/9781119723950.ch20

Seunghyun Yoon, Jin-Hee Cho, Gaurav Dixit, I. Chen

{"title":"Resource‐Aware Intrusion Response Based on Deep Reinforcement Learning for Software‐Defined Internet‐of‐Battle‐Things","authors":"Seunghyun Yoon, Jin-Hee Cho, Gaurav Dixit, I. Chen","doi":"10.1002/9781119723950.ch20","DOIUrl":"https://doi.org/10.1002/9781119723950.ch20","url":null,"abstract":"In this chapter, we propose a resource‐aware active defense framework for software‐defined networking (SDN)‐based Internet‐of‐Battle‐Things (IoBT) by leveraging the advanced features of deep reinforcement learning (DRL). The proposed framework aims to build a highly attack‐resistant network against both physical and cyberspace epidemic attacks. Since typically not all nodes are fully utilized to accomplish a mission, nodes with low utilities can be discarded when they have failed or have been compromised, instead of repairing or replacing them, for a resource‐constrained tactical network assigned with a time‐sensitive mission. However, highly critical and capable nodes should be protected with high priority in order to maximize system security and mission completion rate in the given tactical network. Considering severe resource constraints in IoBT consisting of highly heterogeneous entities under high hostility and network dynamics, we proposed two resource‐aware defense techniques: (1) a multilayer defense network architecture that can construct a network topology based on the importance levels of nodes to provide more security protection for more important nodes which can maximize both security and mission performance (e.g. service availability); and (2) a resource‐aware intrusion response framework that can determine an optimal response action(destruction, repair, or replacement) in response to a detected failure/attack. We conduct a comparative analysis of multiple DRL algorithms against baseline schemes to demonstrate the superiority of our proposed DRL‐based intrusion response strategies not only in system security (e.g. mean time to security failure, MTTSF) and performance (e.g. correct message delivery ratio for mission completion) but also in the accumulated reward obtainable by the system.","PeriodicalId":332247,"journal":{"name":"Game Theory and Machine Learning for Cyber Security","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129801302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Honeypot Allocation Games over Attack Graphs for Cyber Deception 网络欺骗攻击图上的蜜罐分配博弈

Game Theory and Machine Learning for Cyber Security Pub Date : 2021-09-12 DOI: 10.1002/9781119723950.ch4

Ahmed H. Anwar, C. Kamhoua, Nandi O. Leslie, Christopher Kiekintveld

引用次数: 1