領(lǐng)域獨(dú)立智能規(guī)劃技術(shù)及其面向自動化滲透測試的攻擊路徑發(fā)現(xiàn)研究進(jìn)展

臧藝超; 周天陽; 朱俊虎; 王清賢

doi:10.11999/JEIT191056

領(lǐng)域獨(dú)立智能規(guī)劃技術(shù)及其面向自動化滲透測試的攻擊路徑發(fā)現(xiàn)研究進(jìn)展

doi: 10.11999/JEIT191056

臧藝超¹,
周天陽^1, ,,
朱俊虎^{1, 2},
王清賢¹

1.
數(shù)學(xué)工程與先進(jìn)計算國家重點(diǎn)實(shí)驗(yàn)室(信息工程大學(xué)) 鄭州 450001
2.
國家數(shù)字交換系統(tǒng)工程技術(shù)研究中心鄭州 450001

基金項目: 國家自然科學(xué)基金(61502528)

詳細(xì)信息

作者簡介:
臧藝超：男，1991年生，博士生，研究方向?yàn)槁窂揭?guī)劃，強(qiáng)化學(xué)習(xí)，效果評估

周天陽：男，1979年生，副教授，研究方向?yàn)榫W(wǎng)絡(luò)安全，強(qiáng)化學(xué)習(xí)，效果評估

朱俊虎：男，1971年生，教授，研究方向?yàn)榫W(wǎng)絡(luò)安全，網(wǎng)絡(luò)模擬與效果評估

王清賢：男，1960年生，教授，研究方向?yàn)榫W(wǎng)絡(luò)安全，計算復(fù)雜度，網(wǎng)絡(luò)模擬與效果評估

通訊作者:
周天陽　aipteamzhouty@aliyun.com

中圖分類號: TN915.08; TP309
計量
- 文章訪問數(shù): 2775
- HTML全文瀏覽量: 1269
- PDF下載量: 295
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2019-12-31
- 修回日期: 2020-03-17
- 網(wǎng)絡(luò)出版日期: 2020-07-21
- 刊出日期: 2020-09-27

Domain-Independent Intelligent Planning Technology and Its Application to Automated Penetration Testing Oriented Attack Path Discovery

1.
State Key Laboratory of Mathematical Engineering and Advanced Computing, Information & Engineering University, Zhengzhou 450001, China
2.
National Engineering Technology Research Center of the National Digital Switching System, Zhengzhou 450001, China

Funds: The National Natural Science Foundation of China (61502528)

摘要

摘要: 攻擊路徑發(fā)現(xiàn)是自動化滲透測試領(lǐng)域的重要研究方向。該文綜合論述了領(lǐng)域獨(dú)立智能規(guī)劃技術(shù)在面向自動化滲透測試的攻擊路徑發(fā)現(xiàn)上的研究進(jìn)展及應(yīng)用前景。首先介紹了攻擊路徑發(fā)現(xiàn)的基本概念并按照技術(shù)原理將其劃分為基于領(lǐng)域相關(guān)和領(lǐng)域獨(dú)立規(guī)劃技術(shù)的攻擊路徑發(fā)現(xiàn)方法。然后介紹了領(lǐng)域獨(dú)立智能規(guī)劃算法，包括確定性規(guī)劃算法、非確定性規(guī)劃算法和博弈規(guī)劃的技術(shù)原理和發(fā)展?fàn)顩r并就各類方法在攻擊路徑發(fā)現(xiàn)中的應(yīng)用進(jìn)行了綜述。接著分析總結(jié)了滲透測試過程的特點(diǎn)，對比了領(lǐng)域獨(dú)立智能規(guī)劃算法應(yīng)用在面向自動化滲透測試的攻擊路徑發(fā)現(xiàn)時的優(yōu)缺點(diǎn)。最后對攻擊路徑發(fā)現(xiàn)將來的發(fā)展方向進(jìn)行了總結(jié)和展望，希望對未來進(jìn)一步的研究工作有一定的參考價值。
- 領(lǐng)域獨(dú)立智能規(guī)劃技術(shù) /
- 自動化滲透測試 /
- 攻擊路徑發(fā)現(xiàn)
Abstract: Attack path discovery is an important research direction in automated penetration testing area. This paper introduces the research progress of domain independent intelligent planning technology and its application to the field of automated penetration testing oriented attack paths discovery. Firstly, the basic concept of attack path discovery is introduced and the related algorithms are divided into domain-specific and domain-independent intelligent planning based attack path discovery algorithms separately. Secondly, the domain-independent planning algorithms are classified into deterministic planning, uncertain planning and game planning, where each of which is described from principle, development and application aspect in detail. Thirdly, this paper summarizes the characteristics of automated penetration testing and compares the advantages and disadvantages of domain independent intelligent planning algorithms adopted in automated penetration testing. Lastly, the development of automated penetration testing oriented attack path discovery is prospected. It is hoped that this paper could contribute future research works on attack path discovery.
- Domain independent intelligent planning technology /
- Automated penetration testing /
- Attack path discovery

HTML全文

表 1 領(lǐng)域獨(dú)立智能規(guī)劃算法進(jìn)行攻擊路徑發(fā)現(xiàn)時的適用性總結(jié)

	類型	文獻(xiàn)	O	U	D	R	M	優(yōu)點(diǎn)	缺點(diǎn)
確定性攻擊路徑發(fā)現(xiàn)	規(guī)劃圖	[18]	√	×	×	×	√	能夠顯示描述所有可能攻擊路徑，可解釋性強(qiáng)	時間復(fù)雜度高，為O(mn^k)，m為狀態(tài)空間大小，n為動作空間大小，k為層數(shù)
	規(guī)劃圖	[20]	√	×	×	×	√	基于規(guī)劃圖構(gòu)建啟發(fā)函數(shù)，提高攻擊路徑發(fā)現(xiàn)效率	時間復(fù)雜度高，為O(mⁿ)，不適用于大規(guī)模場景m為狀態(tài)空間大小，n為動作空間大小
	偏序規(guī)劃	[22]	√	×	×	×	×	能夠發(fā)現(xiàn)所有動作對之間的約束關(guān)系	需要遍歷動作空間，構(gòu)建約束集合，造成額外時間開銷
	偏序規(guī)劃	[24]	√	×	×	×	√	構(gòu)造啟發(fā)函數(shù)選擇動作，并利用約束關(guān)系縮減規(guī)模，提高路徑搜索效率
	分層任務(wù)網(wǎng)絡(luò)	[30]	√	×	×	×	×	可解釋性更強(qiáng)	需要專家制定分解方法
	分層任務(wù)網(wǎng)絡(luò)	[31]	√	×	×	×	√	利用標(biāo)準(zhǔn)優(yōu)化算法提高路徑發(fā)現(xiàn)效率	需要專家制定分解方法
非確定性攻擊路徑發(fā)現(xiàn)	Determinizing	[36]	√	√	×	×	×	可擴(kuò)展性好，適用多種非確定性場景	無法進(jìn)行重規(guī)劃
	概率優(yōu)化	[41]	√	√	×	×	×	能夠根據(jù)實(shí)際執(zhí)行結(jié)果進(jìn)行重規(guī)劃	需要刪除非確定性信息進(jìn)行規(guī)劃，無法利用規(guī)劃反饋信息
	概率優(yōu)化	[44]	√	×	×	×	√	構(gòu)造規(guī)劃圖啟發(fā)函數(shù)，求解效率高	構(gòu)建多個規(guī)劃圖，造成大量冗余
	馬爾可夫決策過程	[52]	√	√	×	×	√	能存儲大規(guī)模網(wǎng)絡(luò)空間狀態(tài)策略，策略求解效率更高	容易陷入局部極小值
	馬爾可夫決策過程	[53]	√	√	×	×	√	基于數(shù)據(jù)確定模型的參數(shù)個數(shù)和函數(shù)形式，無需人工設(shè)定，靈活方便	在較大數(shù)據(jù)集的情況下訓(xùn)練時間較長
	部分觀測的馬爾可夫決策過程	[55]	√	√	×	×	√	精確求解算法，是后續(xù)近似求解算法的基礎(chǔ)	求解復(fù)雜度極高，當(dāng)狀態(tài)空間較大時無法進(jìn)行規(guī)劃求解
		[57]	√	√	×	×	√	首個基于點(diǎn)迭代的近似求解方法，求解效率相對于精確求解效率高	僅能對單主機(jī)進(jìn)行規(guī)劃，時間復(fù)雜度O(\|N\|\|A\|(\|S\|\|B\|+\|O\|))，其中S為狀態(tài)集合，A為動作集合，O為觀測狀態(tài)集合，B為信念狀態(tài)點(diǎn)集合，N為上限點(diǎn)集合
		[58]	√	√	×	×	√	采用前向搜索策略，采樣效率更高，適合短序列場景	僅能對單主機(jī)進(jìn)行規(guī)劃，時間復(fù)雜度O(\|N\|(\|S\|²+\|A\|+\|O\|))其中S為狀態(tài)集合，A為動作集合，O為觀測狀態(tài)集合，N為上限點(diǎn)集合
		[59]	√	√	×	×	√	采樣效率高	僅能對單主機(jī)進(jìn)行規(guī)劃，無法擴(kuò)展到網(wǎng)絡(luò)層面，時間復(fù)雜度為O(\|S\|³\|A\|\|O\|\|B\|\|N\|)其中S為狀態(tài)集合，A為動作集合，O為觀測狀態(tài)集合，B為信念狀態(tài)點(diǎn)集合，N為上限點(diǎn)集合
		[60]	√	√	×	×	√	能夠?qū)崿F(xiàn)網(wǎng)絡(luò)層面攻擊路徑發(fā)現(xiàn)	假定網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu)及策略穩(wěn)定不變
博弈攻擊路徑發(fā)現(xiàn)	靜態(tài)博弈模型	[62]	√	×	×	×	√	首次將博弈模型引入到攻防對抗	要求完全信息且攻防雙方為完全理性，并且要求攻防對抗策略保持不變
	靜態(tài)博弈模型	[63]	√	×	×	×	√	求解效率高	要求完全信息且攻防雙方為完全理性，并且要求攻防對抗策略保持不變
	動態(tài)博弈模型	[67]	√	×	√	×	√	多輪次博弈條件下的攻擊路徑發(fā)現(xiàn)	要求完全信息且攻防雙方為完全理性
		[68]	√	×	√	×	√	摒棄了完全理性和完全信息假設(shè)	復(fù)雜度較高，為O((m+n)²)，m和n分別為攻防策略集合大小
		[71]	√	×	√	×	√	摒棄了攻防雙方對等信息的假設(shè)	模型復(fù)雜，求解難，現(xiàn)實(shí)應(yīng)用場景受限
注：O：狀態(tài)空間完備性；U：行為不確定性；D:過程動態(tài)性；R：資源約束性；M：路徑最優(yōu)性。

下載: 導(dǎo)出CSV

參考文獻(xiàn)(72)

KRUTZ R L and VINES R D. The CISSP and CAP Prep guide: Platinum Edition[M]. New Jersey: Wiley, 2007.

STEFINKO Y, PISKOZUB A, and BANAKH R. Manual and automated penetration testing. Benefits and drawbacks. Modern tendency[C]. The 13th International Conference on Modern Problems of Radio Engineering, Telecommunications and Computer Science, Lviv, Ukraine, 2016: 488–491. doi: 10.1109/tcset.2016.7452095.

ABU-DABASEH F and ALSHAMMARI E. Automated penetration testing: An overview[C]. The 4th International Conference on Natural Language Computing, Copenhagen, Denmark, 2018: 121–129.

MCDERMOTT J P. Attack net penetration testing[C]. 2000 Workshop on New Security Paradigms, Ballycotton, Ireland, 2001: 15–21. doi: 10.1145/366173.366183.

諸葛建偉, 陳力波, 孫松柏, 等. Metasploit滲透測試魔鬼訓(xùn)練營[M]. 北京: 機(jī)械工業(yè)出版社, 2013: 3–4.

ZHUGE Jianwei, CHEN Libo, SUN Songbai, et al. Penetration Testing Devil Training Camp Based on Metasploit[M]. Beijing: China Machine Press, 2013: 3–4.

POLATIDIS N, PAVLIDIS M, and MOURATIDIS H. Cyber-attack path discovery in a dynamic supply chain maritime risk management system[J]. Computer Standards & Interfaces, 2018, 56: 74–82. doi: 10.1016/j.csi.2017.09.006

李慶華, 尤越, 沐雅琪, 等. 一種針對大型凹型障礙物的組合導(dǎo)航算法[J]. 電子與信息學(xué)報, 2020, 42(4): 917–923. doi: 10.11999/JEIT190179

LI Qinghua, YOU Yue, MU Yaqi, et al. Integrated navigation algorithm for large concave obstacles[J]. Journal of Electronics &Information Technology, 2020, 42(4): 917–923. doi: 10.11999/JEIT190179

BIALEK ?, DUNIN-K?PLICZ B, and SZA?AS A. A paraconsistent approach to actions in informationally complex environments[J]. Annals of Mathematics and Artificial Intelligence, 2019, 86(4): 231–255. doi: 10.1007/s10472-019-09627-9

AMMANN P, WIJESEKERA D, and KAUSHIK S. Scalable, Graph-based network vulnerability analysis[C]. The 9th ACM Conference on Computer and Communications Security, Washington, USA, 2002: 217–224. doi: 10.1145/586110.586140.

CHEN Feng, LIU Dehui, ZHANG Yi, et al. A scalable approach to analyzing network security using compact attack graphs[J]. Journal of Networks, 2010, 5(5): 543–550. doi: 10.4304/jnw.5.5.543-550

OU Xinming, GOVINDAVAJHALA S, and APPEL A W. MulVAL: A logic-based network security analyzer[C]. The 14th Conference on USENIX Security Symposium, Baltimore, USA, 2005: 113–128.

WANG Lingyu, YAO Chao, SINGHAL A, et al. Interactive analysis of attack graphs using relational queries[C]. The 20th Annual Conference on Data and Applications Security and Privacy, Sophia Antipolis, France, 2006: 119–132. doi: 10.1007/11805588_9.

LI Wei, VAUGHN R B, and DANDASS Y S. An approach to model network exploitations using exploitation graphs[J] Simulation, 2006, 82(8): 523–541. doi: 10.1177/0037549706072046.

MAHDAVI A and CARVALHO M. Optimal trajectory and schedule planning for autonomous guided vehicles in flexible manufacturing system[C]. The 2nd IEEE International Conference on Robotic Computing, Laguna Hills, USA, 2018: 167–172. doi: 10.1109/irc.2018.00034.

MA Xiaobai, JIAO Ziyuan, WANG Zhenkai, et al. 3-D decentralized prioritized motion planning and coordination for high-density operations of micro aerial vehicles[J]. IEEE Transactions on Control Systems Technology, 2018, 26(3): 939–953. doi: 10.1109/tcst.2017.2699165

ZANG Yichao, ZHOU Tianyang, GE Xiaoyue, et al. An improved attack path discovery algorithm through compact graph planning[J]. IEEE Access, 2019, 7: 59346–59356. doi: 10.1109/access.2019.2915091

BODDY M S, GOHDE J, HAIGH T, et al. Course of action generation for cyber security using classical planning[C]. The 15th International Conference on Automated Planning and Scheduling, Monterey, USA, 2005: 12–21.

GARRETT C R, LOZANO-PéREZ T, and KAELBLING L P. FFRob: Leveraging symbolic planning for efficient task and motion planning[J]. The International Journal of Robotics Research, 2018, 37(1): 104–136. doi: 10.1177/0278364917739114

KAUTZ H A and SELMAN B. Unifying SAT-based and graph-based planning[C]. The 16th International Joint Conference on Artificial Intelligence, Stockholm, Sweden, 1999: 318–325.

DO M B and KAMBHAMPATI S. Planning as constraint satisfaction: Solving the planning graph by compiling it into CSP[J]. Artificial Intelligence, 2001, 132(2): 151–182. doi: 10.1016/s0004-3702(01)00128-x

BAIOLETTI M, MARCUGINI S, and MILANI A. DPPlan: An algorithm for fast solutions extraction from a planning graph[C]. The 5th International Conference on Artificial Intelligence Planning Systems, Breckenridge, USA, 2000: 13–21.

BARRETT A and WELD D S. Partial-order planning: Evaluating possible efficiency gains[J]. Artificial Intelligence, 1994, 67(1): 71–112. doi: 10.1016/0004-3702(94)90012-4

NGUYEN X L and KAMBHAMPATI S. Reviving partial order planning[C]. The 17th International Joint Conference on Artificial Intelligence, Seattle, USA. 2001: 459–466.

YOUNES H L S and SIMMONS R G. VHPOP: Versatile heuristic partial order planner[J]. Journal of Artificial Intelligence Research, 2003, 20: 405–430. doi: 10.1613/jair.1136

COLES A J, COLES A, FOX M, et al. Forward-chaining partial-order planning[C]. The 20th International Conference on Automated Planning and Scheduling, Toronto, Canada, 2010: 42–49.

BOUTILIER C and BRAFMAN R I. Partial-order planning with concurrent interacting actions[J]. Journal of Artificial Intelligence Research, 2001, 14: 105–136. doi: 10.1613/jair.740

MOHR F, WEVER M, and HüLLERMEIER E. ML-Plan: Automated machine learning via hierarchical planning[J]. Machine Learning, 2018, 107(8–10): 1495–1515. doi: 10.1007/s10994-018-5735-z

DE SILVA L, PADGHAM L, and SARDINA S. HTN-like solutions for classical planning problems: An application to BDI agent systems[J]. Theoretical Computer Science, 2019, 763: 12–37. doi: 10.1016/j.tcs.2019.01.034

SOHN S, OH J, and LEE H. Hierarchical reinforcement learning for zero-shot generalization with subtask dependencies[C]. The 32nd Conference on Neural Information Processing Systems, Montréal, Canada, 2018: 7156–7166.

MU Chengpo and LI Yingjiu. An intrusion response decision-making model based on hierarchical task network planning[J]. Expert Systems with Applications, 2010, 37(3): 2465–2472. doi: 10.1016/j.eswa.2009.07.079

ONTA?óN S and BURO M. Adversarial hierarchical-task network planning for complex real-time games[C]. The 24th International Joint Conference on Artificial Intelligence, Buenos Aires, Argentina, 2015: 1652–1658.

FU JICHENG, NG V, BASTANI F B, et al. Simple and fast strong cyclic planning for fully-observable nondeterministic planning problems[C]. The 22nd International Joint Conference on Artificial Intelligence, Barcelona, Spain, 2011: 1949–1954. doi: 10.1007/s10472-016-9517-7.

KOLOBOV A, MAUSAM M, and Weld D S. LRTDP versus UCT for online probabilistic planning[C]. The 26th AAAI Conference on Artificial Intelligence, Toronto, Canada, 2012: 1786–1792.

YOON S, FERN A, GIVAN R, et al. Probabilistic planning via determinization in hindsight[C]. The 23rd AAAI Conference on Artificial Intelligence, Chicago, USA, 2008: 1010–1016.

CIMATTI A, PISTORE M, ROVERI M, et al. Weak, strong, and strong cyclic planning via symbolic model checking[J]. Artificial Intelligence, 2003, 147(1/2): 35–84. doi: 10.1016/s0004-3702(02)00374-0

MUISE C J, MCILRAITH S A, and BECK J C. Improved non-deterministic planning by exploiting state relevance[C]. The 22nd International Conference on Automated Planning and Scheduling, Atibaia, Brazil, 2012: 172–180.

MUISE C J, MCILRAITH S A, and BELLE V. Non-deterministic planning with conditional effects[C]. The 24th International Conference on Automated Planning and Scheduling, Portsmouth, USA, 2014: 370–374.

李洋, 文中華, 伍小輝, 等. 求最小期望權(quán)值強(qiáng)循環(huán)規(guī)劃解[J]. 計算機(jī)科學(xué), 2015, 42(4): 217–220, 257. doi: 10.11896/j.issn.1002-137X.2015.04.044

LI Yang, WEN Zhonghua, WU Xiaohui, et al. Solving strong cyclic planning with minimal expectation weight[J]. Computer Science, 2015, 42(4): 217–220, 257. doi: 10.11896/j.issn.1002-137X.2015.04.044

唐杰, 文中華, 汪泉, 等. 不確定可逆規(guī)劃的強(qiáng)循環(huán)規(guī)劃解[J]. 計算機(jī)研究與發(fā)展, 2013, 50(9): 1970–1980. doi: 10.7544/issn1000-1239.2013.20130404

TANG Jie, WEN Zhonghua, WANG Quan, et al. Solving strong cyclic planning in nondeterministic reversible planning domain[J]. Journal of Computer Research and Development, 2013, 50(9): 1970–1980. doi: 10.7544/issn1000-1239.2013.20130404

KUSHMERICK N, HANKS S, and WELD D S. An algorithm for probabilistic planning[J]. Artificial Intelligence, 1995, 76(1/2): 239–286. doi: 10.1016/0004-3702(94)00087-H

YOON S W, FERN A, and GIVAN R. FF-Replan: A baseline for probabilistic planning[C]. The 17th International Conference on Automated Planning and Scheduling, Providence, USA, 2007: 352–359.

YOON S, RUML W, BENTON J, et al. Improving determinization in hindsight for on-line probabilistic planning[C]. The 20th International Conference on Automated Planning and Scheduling, Toronto, Canada, 2010: 209–216.

ISSAKKIMUTHU M, FERN A, KHARDON R, et al. Hindsight optimization for probabilistic planning with factored actions[C]. The 25th International Conference on Automated Planning and Scheduling, Jerusalem, Israel, 2015: 120–128.

BRYCE D, KAMBHAMPATI S, and SMITH D E. Sequential Monte Carlo in probabilistic planning reachability heuristics[C]. The 16th International Conference on Automated Planning and Scheduling, Cumbria, UK, 2006: 233–242.

TREVIZAN F W, THIéBAUX S, and HASLUM P. Occupation measure heuristics for probabilistic planning[C]. The 27th International Conference on Automated Planning and Scheduling, Pittsburgh, USA, 2017: 306–315.

DURKOTA K and LISY V. Computing optimal policies for attack graphs with action failures and costs[C]. The 7th European Starting AI Researcher Symposium, Prague, Czech Republic, 2014: 101–110.

SUN Wen, GORDON G J, BOOTS B, et al. Dual policy iteration[C]. The 32nd Conference on Neural Information Processing Systems, Montréal, Canada, 2018: 7059–7069.

HOUTHOOFT R, CHEN R Y, ISOLA P, et al. Evolved policy gradients[C]. The 32nd International Conference on Neural Information Processing Systems, Montréal, Canada, 2018: 5405–5414.

LIU Huaping, WU Yupei, and SUN Fuchun. Extreme trust region policy optimization for active object recognition[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(6): 2253–2258. doi: 10.1109/TNNLS.2017.2785233

SRINIVASAN S, LANCTOT M, ZAMBALDI V, et al. Actor-critic policy optimization in partially observable multiagent environments[C]. The 32nd Conference on Neural Information Processing Systems, Montréal, Canada, 2018: 3422–3435.

KANG Qinma, ZHOU Huizhuo, and KANG Yunfan. An asynchronous advantage actor-critic reinforcement learning method for stock selection and portfolio management[C]. The 2nd International Conference on Big Data Research, Weihai, China, 2018: 141–145. doi: 10.1145/3291801.3291831.

TAN Fuxiao and GUAN Xinping. Kernel-based adaptive critic designs for optimal control of nonlinear discrete-time system[C]. The 37th Chinese Control Conference, Wuhan, China, 2018: 2167–2172. doi: 10.23919/chicc.2018.8482778.

TAYLOR G and PARR R. Kernelized value function approximation for reinforcement learning[C]. The 26th Annual International Conference on Machine Learning, Montreal, Canada, 2009: 1017–1024. doi: 10.1145/1553374.1553504.

SARRAUTE C, BUFFET O, and HOFFMANN J. Penetration testing== POMDP solving?[C]. 2011 IJCAI Workshop on Intelligent Security, Barcelona, Spain, 2011: 66–73.

SMALLWOOD R D and SONDIK E J. The optimal control of partially observable Markov processes over a finite horizon[J]. Operations Research, 1973, 21(5): 1071–1088. doi: 10.1287/opre.21.5.1071

CHENG H T. Algorithms for partially observable Markov decision processes[D]. [Ph. D. dissertation], The University of British Columbia, 1988. doi: 10.14288/1.0098252.

PINEAU J, GORDON G, and THRUN S. Point-based value iteration: An anytime algorithm for POMDPs[C]. The 18th International Joint Conference on Artificial Intelligence, Acapulco, Mexico, 2003: 1025–1032.

LIU Bingbing, KANG Yu, JIANG Xiaofeng, et al. A fast approximation method for partially observable Markov decision processes[J]. Journal of Systems Science and Complexity, 2018, 31(6): 1423–1436. doi: 10.1007/s11424-018-7038-7

KURNIAWATI H, HSU D, LEE W S. SARSOP: Efficient point-based POMDP planning by approximating optimally reachable belief spaces[C]. The Robotics: Science and Systems IV, Zurich, Switzerland, 2008: 65–72. doi: 10.15607/RSS.2008.IV.009.

SARRAUTE C, BUFFET O, and HOFFMANN J. POMDPs make better hackers: Accounting for uncertainty in penetration testing[C]. The 26th AAAI Conference on Artificial Intelligence, Toronto, Canada, 2012: 1816–1824.

王剛, 胡鑫, 馬潤年, 等. 集體防御機(jī)制下的網(wǎng)絡(luò)行動同步建模和穩(wěn)定性[J]. 電子與信息學(xué)報, 2018, 40(6): 1515–1519. doi: 10.11999/JEIT170619

WANG Gang, HU Xin, MA Runnian, et al. Synchronization modeling and stability of cyberspace operation based on collective defensive mechanism[J]. Journal of Electronics &Information Technology, 2018, 40(6): 1515–1519. doi: 10.11999/JEIT170619

LYE K W and WING J M. Game strategies in network security[J]. International Journal of Information Security, 2005, 4(1/2): 71–86. doi: 10.1007/s10207-004-0060-x

姜偉, 方濱興, 田志宏, 等. 基于攻防博弈模型的網(wǎng)絡(luò)安全測評和最優(yōu)主動防御[J]. 計算機(jī)學(xué)報, 2009, 32(4): 817–827. doi: 10.3724/SP.J.1016.2009.00817

JIANG Wei, FANG Binxing, TIAN Zhihong, et al. Evaluating network security and optimal active defense based on attack-defense game model[J]. Chinese Journal of Computers, 2009, 32(4): 817–827. doi: 10.3724/SP.J.1016.2009.00817

王晉東, 余定坤, 張恒巍, 等. 靜態(tài)貝葉斯博弈主動防御策略選取方法[J]. 西安電子科技大學(xué)學(xué)報: 自然科學(xué)版, 2016, 43(1): 144–150. doi: 10.3969/j.issn.1001-2400.2016.01.026

WANG Jindong, YU Dingkun, ZHANG Hengwei, et al. Active defense strategy selection based on the static Bayesian game[J]. Journal of Xidian University, 2016, 43(1): 144–150. doi: 10.3969/j.issn.1001-2400.2016.01.026

王元卓, 林闖, 程學(xué)旗, 等. 基于隨機(jī)博弈模型的網(wǎng)絡(luò)攻防量化分析方法[J]. 計算機(jī)學(xué)報, 2010, 33(9): 1748–1762. doi: 10.3724/SP.J.1016.2010.01748

WANG Yuanzhuo, LIN Chuang, CHENG Xueqi, et al. Analysis for network attack-defense based on stochastic game model[J]. Chinese Journal of Computers, 2010, 33(9): 1748–1762. doi: 10.3724/SP.J.1016.2010.01748

CUI Xiaolin, TAN Xiaobin, ZHANG Yong, et al. A Markov game theory-based risk assessment model for network information system[C]. 2008 International Conference on Computer Science and Software Engineering, Hubei, China, 2008: 1057–1061. doi: 10.1109/csse.2008.949.

LI Tao, WANG Jindong, CHEN Yu, et al. A multi-stage game approach applied to network security risk controlling[C]. The 2nd IEEE Advanced Information Technology, Electronic and Automation Control Conference, Chongqing, China, 2017: 2518–2522. doi: 10.1109/iaeac.2017.8054477.

黃健明, 張恒巍, 王晉東, 等. 基于攻防演化博弈模型的防御策略選取方法[J]. 通信學(xué)報, 2017, 38(1): 168–176. doi: 10.11959/j.issn.1000-436x.2017019

HUANG Jianming, ZHANG Hengwei, Wang Jindong, et al. Defense strategies selection based on attack-defense evolutionary game model[J]. Journal on Communications, 2017, 38(1): 168–176. doi: 10.11959/j.issn.1000-436x.2017019

張恒巍, 李濤. 基于多階段攻防信號博弈的最優(yōu)主動防御[J]. 電子學(xué)報, 2017, 45(2): 431–439. doi: 10.3969/j.issn.0372-2112.2017.02.023

ZHANG Hengwei and LI Tao. Optimal active defense based on multi-stage attack-defense signaling game[J]. Acta Electronica Sinica, 2017, 45(2): 431–439. doi: 10.3969/j.issn.0372-2112.2017.02.023

朱建明, 宋彪, 黃啟發(fā). 基于系統(tǒng)動力學(xué)的網(wǎng)絡(luò)安全攻防演化博弈模型[J]. 通信學(xué)報, 2014, 35(1): 54–61. doi: 10.3969/j.issn.1000-436x.2014.01.007

ZHU Jianming, SONG Biao, and HUANG Qifa. Evolution game model of offense-defense for network security based on system dynamics[J]. Journal on Communications, 2014, 35(1): 54–61. doi: 10.3969/j.issn.1000-436x.2014.01.007

VADLAMUDI S G, SENGUPTA S, TAGUINOD M, et al. Moving target defense for web applications using Bayesian stackelberg games: (Extended Abstract)[C]. The 2016 International Conference on Autonomous Agents & Multiagent Systems, Singapore, 2016: 1377–1378.

YUAN Yuan, SUN Fuchun, and LIU Huaping. Resilient control of cyber-physical systems against intelligent attacker: A hierarchal stackelberg game approach[J]. International Journal of Systems Science, 2016, 47(9): 2067–2077. doi: 10.1080/00207721.2014.973467

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計