网络安全遇上人工智能:综述（英文）

被引：13

作者：

Jian-hua LI

机构：

[1] SchoolofCyberSecurity,ShanghaiJiaoTongUniversity

来源：

FrontiersofInformationTechnology&ElectronicEngineering | 2018年 / 19卷 / 12期

关键词：

网络安全; 人工智能; 攻击监测; 防御技术;

D O I：

暂无

中图分类号：

TP393.08 []; TP18 [人工智能理论];

学科分类号：

0839 ; 1402 ; 081104 ; 0812 ; 0835 ; 1405 ;

摘要：

网络安全与人工智能技术有着广泛的交叉。一方面,可以将人工智能技术(如深度学习)引入网络安全领域,构建智能模型,实现恶意代码检测、入侵检测和威胁情报感知等。另一方面,人工智能模型面临针对样本、学习过程和决策等的各种威胁。因此,人工智能模型需要网络安全防护技术来对抗各类攻击,实现隐私保护机器学习以及安全的联合深度学习等。本文对人工智能与网络安全交叉研究进行综述,首先总结现有利用人工智能技术对抗网络攻击的研究工作,包括采用传统机器学习技术和深度学习技术在对抗网络攻击方面的应用和效果。然后总结和分析人工智能会遭受的对抗攻击,对现有针对对抗攻击的防御方式进行归类,分析各自特点。最后,从构建加密神经网络和实现安全联合深度学习两个方面阐述现有工作中构建安全人工智能系统的方案。

引用

页码：1462 / 1475

页数：14

共 66 条

[1] A unified gradient regularization family for adversarial examples. Lyu C,Huang KZ,Liang HN. IEEE Int Conf on Data Mining . 2015
[2] The limitations of deep learning in adversarial settings. PAPERNOT N,MCDANIEL P,JHA S,et al. IEEE European Symposium on Security and Privacy . 2016
[3] Adversarial manipulation of deep representations. Sabour S,Cao YS,Faghri F,et al. https://arxiv.org/abs/ 1511.05122 . 2015
[4] Threat of adversarial attacks on deep learning in computer vision:a survey. AKHTAR N,MIAN A. IEEE Access . 2018
[5] Biologically inspired protection of deep networks from adversarial attacks. Nayebi A,Ganguli S. https://arxiv.org/abs/ 1703.09202 . 2017
[6] Identification and evaluation of discriminative lexical features of malware URL for real-time classification. Olalere M,Abdullah MT,Mahmod R,et al. Int Conf on Computer and Communication Engineering . 2016
[7] Adversarial examples for semantic segmentation and object detection. Xie CH,Wang JY,Zhang ZS,et al. IEEE Int Conf on Computer Vision . 2017
[8] "Deep learning:The frontier for dis-tributed attack detection in fog-to-things computing,". A.Abeshu,N.Chilamkurti. IEEE Communications Magazine . 2018
[9] Design of intelligent KNN-based alarm filter using knowledge-based alert verification in intrusion detection
Meng, Weizhi
Li, Wenjuan
Kwok, Lam-For
[J]. SECURITY AND COMMUNICATION NETWORKS, 2015, 8 (18) : 3883 - 3895
[10] Generative adversarial networks. Goodfellow IJ,Pouget-Abadie J,Mirza M,et al. https://arxiv.org/abs/ 1406.2661 . 2014

← 1 2 3 4 5 6 7 →