PDF(441 KB)
PDF(441 KB)
PDF(441 KB)
基于人工智能的网络空间安全防御战略研究
Artificial Intelligence Enabled Cyberspace Security Defense
网络空间是继陆、海、空、天之后的第五大活动空间，维护网络空间安全是事关国家安全、国家主权和人民群众合法权益的重大问题。随着人工智能技术的飞速发展和在各领域的应用，网络空间安全面临着新的挑战。本文分析了人工智能时代网络空间安全面临的新风险，包括网络攻击越来越智能化，大规模网络攻击越来越频繁，网络攻击的隐蔽性越来越高，网络攻击的对抗博弈越来越强，重要数据越来越容易被窃取等；介绍了人工智能技术在处理海量数据、多源异构数据、实时动态数据时具有显著的优势，能大幅度提升网络空间防御能力；基于人工智能的网络空间防御关键问题及技术，重点分析了网络安全知识大脑的构建及网络攻击研判，并从构建动态可扩展的网络安全知识大脑，推动有效网络攻击的智能化检测，评估人工智能技术的安全性三个方面提出了针对性的发展对策和建议。
Cyberspace is regarded as the fifth largest activity space following land, sea, air, and space. Protecting cyberspace security is a major issue related to national security, national sovereignty, and the legitimate rights and interests of the people. With the rapid development of artificial intelligence (AI) technology and its application in various fields, cyberspace security has been facing new challenges. This study analyzes the new risks of cyberspace security in the era of AI, such as more intelligent network attacks, more frequent large-scale network attacks, higher concealment of network attacks, stronger confrontation game of network attacks, and easier exposure to stealing of important data. AI technology has significant advantages in dealing with massive data, multi-source heterogeneous data, and real-time dynamic data, which can significantly improve the defense capability of cyberspace. This study introduces some key problems and technologies of AI-enabled cyberspace security defense, particularly the construction of a cyberspace security knowledge brain and the detection of network attacks. Furthermore, we propose the corresponding countermeasures and suggestions from three aspects: the construction of a dynamic and scalable network security knowledge brain, the promotion of intelligent detection against network attacks, and the evaluation of AI technologies’ security.
artificial intelligence (AI) / cyberspace security / cyber attacks / cyber defense
| [1] |
方滨兴. 人工智能安全 [M]. 北京：电子工业出版社, 2020. Fang B X. Artificial intelligence security and safety [M]. Beijing: Publishing House of Electronics Industry, 2020.
|
| [2] |
贾焰, 方滨兴. 网络安全态势感知 [M]. 北京：电子工业出版 社，2020. Jia Y, Fang B X. Network security situation awareness [M]. Beijing: Publishing House of Electronics Industry, 2020.
|
| [3] |
Veeramachaneni K, Arnaldo I, Korrapati V, et al. AI2 : Training a big data machine to defend [C]. New York: IEEE 2nd International Conference on Big Data Security on Cloud (BigDataSecurity), IEEE International Conference on High Performance and Smart Computing (HPSC) and IEEE International Conference on Intelligent Data and Security (IDS), 2016.
|
| [4] |
Hendler D, Kels S, Rubin A. Detecting malicious powershell commands using deep neural networks [C]. Incheon: ACM Asia Conference on Computer and Communications Security, 2018.
|
| [5] |
Manès V J M, Han H, Han C, et al. The art, science, and engineering of fuzzing: A survey [J]. IEEE Transactions on Software Engineering, 2019. doi: 10.1109/TSE.2019.2946563.
|
| [6] |
Brooks T N. Survey of automated vulnerability detection and exploit generation techniques in cyber reasoning systems [EB/ OL]. (2017-02-20) [2021-02-28]. https://arxiv.org/abs/1702.06162.
|
| [7] |
Capture the Flag [EB/OL]. [2021-02-28]. https://defcon.org/html/ defcon-24/dc-24-ctf.html (2016 Defcon CTF Final Scores).
|
| [8] |
Fortinet FortiGuard Labs 2018 Threat Landscape Predictions [EB/OL]. (2017-11-14) [2021-02-28]. https://www.fortinet.com/ blog/business-and-technology/fortinet-fortiguard-2018-threatlandscape-predictions.html (Prediction: The rise of Hivenets and Swarmbots).
|
| [9] |
Kirat D, Jang J Y, Stoecklin M P. DeepLocker-concealing targeted attacks with AI locksmithing [EB/OL]. (2018-08-09) [2021-02- 28]. https://i.blackhat.com/us-18/Thu-August-9/us-18-KiratDeepLocker-Concealing-Targeted-Attacks-with-AI-Locksmithing. pdf.
|
| [10] |
Hu W W, Tan Y. Generating adversarial malware examples for black-box attacks based on gAN [DB/OL]. (2017-02-20) [2021- 02-28]. https://arxiv.org/pdf/1702.05983.pdf.
|
| [11] |
Gu Z Q, Hu W X, Zhang C J, et al. Gradient Shielding: Towards Understanding Vulnerability of Deep Neural Networks [J]. IEEE Transactions on Network Science and Engineering (Early Access), 2020. doi: 10.1109/TNSE.2020.2996738.
|
| [12] |
Gu Z Q, Cai Y Y, Wang S, et al. Adversarial Attacks on ContentBased Filtering Journal Recommender Systems [J]. Computers, Materials & Continua, 2020, 64(3): 1755–1770.
|
| [13] |
Shokri R, Stronati M, Song C Z, et al. Membership inference attacks against machine learning models [C]. San Jose: IEEE Symposium on Security and Privacy, 2017.
|
| [14] |
Zhang Y H, Jia R X, Pei H Z, et al. The secret revealer: Generative model-inversion attacks against deep neural networks [C]. Seattle: IEEE Conference on Computer Vision and Pattern Recognition, 2020.
|
| [15] |
Ji S, Pan S, Cambria E, et al. A survey on knowledge graphs: Representation, acquisition and applications. [DB/OL]. (2020-02- 02)[2021-02-28]. https://arxiv.org/abs/2002.00388.
|
| [16] |
Jia Y, Gu Z Q, Li A, et al. (Eds). MDATA: A new knowledge representation model [M]. Switzerland: Springer International Publishing, 2021.
|
| [17] |
Hinton G E. Learning multiple layers of representation [J]. Trends in Cognitive Sciences, 2007, 11(10): 428–434.
|
| [18] |
Jia Y, Qi Y, Shang H, et al. A practical approach to constructing a knowledge graph for cybersecurity [J]. Engineering, 2018, 4(1):53–60.
|
| [19] |
Qi Y, Zhong J, Jiang R, et al. FSM-based cyber security status analysis method [C]. Hangzhou: IEEE Fourth International Conference on Data Science in Cyberspace (DSC), 2019.
|
/
| 〈 |
|
〉 |
