期刊文献+

人工智能在网络安全领域的辅助应用和面临的挑战 被引量:3

Auxiliary applications and challenges of artificial intelligence in the field of cybersecurity
下载PDF
导出
摘要 人工智能工具用于分析数据和预测结果,其对许多行业都是福音,包括网络安全和国防行业。目前,越来越多的防病毒和网络威胁情报系统正在寻求将人工智能技术集成到网络防御响应能力中。过去网络安全领域的观点认为威胁主要来自于单独的黑客入侵行为,而事实上,我们面对的是有着严密组织的网络犯罪集团[1],勒索软件就是一个典型的例子。传统网络安全领域存在两个重大缺陷:一是非常依赖规则;二是无法根据现代企业的规模进行扩展。但是,人工智能则可凭借其强大的学习和运算能力,迅速地从百万次迥异的嫌疑事件中发现异常、风险和未知威胁的信号。文章阐述该如何利用人工智能、机器学习、深度感知等方法,提升应对网络安全威胁的能力,从而更全面、高效地建设我国的信息安全保障机制,使局部安全服务于国家安全。 Artificial intelligence tools are used to analyze data and predict results.They are good news for many industries,including cybersecurity and defense industries.At present,more and more antivirus and network threat intelligence systems are seeking to integrate artificial intelligence technology into network defense response capabilities.In the past,the point of view in the field of cybersecurity was that the threat mainly came from separate hacking activities.In fact,we are faced with a tightly organized cybercrime group[1].Ransomware is a typical example.There are two major flaws in the traditional cybersecurity field:one is very dependent on rules;the other is that it cannot be expanded according to the scale of modern enterprises.However,artificial intelligence can quickly find signals of anomalies,risks,and unknown threats from millions of very different suspected events with its powerful learning and computing capabilities.This article explains how to use artificial intelligence,machine learning,depth perception and other methods to improve the ability to respond to cybersecurity threats,so as to build a more comprehensive and efficient information security assurance mechanism in my country,so that local security serves national security.
作者 高伟波 李仲琴 Gao Weibo;Li Zhongqin(Brigade no.261,Jiangxi Nuclear Industry Geology Bureau,Jiangxi Yingtan 335001)
出处 《网络空间安全》 2020年第7期86-91,共6页 Cyberspace Security
关键词 人工智能 网络安全 深度学习 artificial intelligence cybersecurity deep learning
  • 相关文献

参考文献1

二级参考文献15

  • 1Gers F A, Sehmidhuber J. LSTM Recurrent Networks Learn Simple Context-Free and Context-Sensitive Languages. IEEE Trans on Neu-ral Networks, 2001, 12(6): 1333-1340.
  • 2Mitchell T M. Machine Learning. New York, USA: McGraw Hill, 1997.
  • 3Yang Jian, Zhang D, Alejandro F, et al. Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition. IEEE Trans on Pattern Analysis and Machine Intelli-gence, 2004, 26(1): 117-129.
  • 4Wachenfeld S, Klein H V, Jiang Xiaoyi. Recognition of Screen-Rendered Text//Proc of the 18th International Conference on Pat-tern Recognition. Hongkong, China, 2006, Ⅱ : 1086-1089.
  • 5von Ahn L, Blum M, Hopper N J, et al. CAPTCHA: Using Hard AI Problems for Security// Proc of the 22nd International Confer-ence on Theory and Applications of Cryptographic Techniques. War-saw, Poland, 2003 : 294-311.
  • 6Rusu A, Thomas A, Govindaraju V. Generation and Use of Hand- written CAPTCHAs. International Journal on Document Analysis and Recognition, 2010,13(1) :49-64.
  • 7Rusu A, Govindaraju V. Handwritten CAPTCHA: Using the Differ-ence in the Abilities of Humans and Machines in Reading Handwrit-ten Words//Proc of the 9th International Workshop on Frontiers in Handwriting Recognition. Tokyo, Japan, 2004 : 226-231.
  • 8von Ahn L, Maurer B, McMillen C, et al. reCAPTCHA: Human-Based Character Recognition via Web Security Measures. Science, 2008, 321 (5895) : 1465-1468.
  • 9Chellapilla K, Simard P. Using Machine Learning to Break Visual Human Interaction Proofs (HIPs) // Weiss Y, Scholkopf B, Platt J, eds. Advances in Neural Information Processing Systems. Cam- bridge, USA: M IT Press, 2004, 17: 265-272.
  • 10Hocevar S. PWNTCHA-Pretend Were Not a Turing Computer But a Human Antagonist [EB/OL]. [2010-02-15]. http ://sam. zoy. org/wiki/PWNtcha.

共引文献24

同被引文献14

引证文献3

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部