Generative Adversarial Networks in Al-Enabled Safety Critical Systems: Friend or Foe?

被引:4
作者
Fournaris, Apostolos P. [1 ]
Lalos, Aris S. [1 ]
Serpanos, Dimitrios [1 ]
机构
[1] RC Athena, Ind Syst Inst, Patras, Greece
基金
欧盟地平线“2020”;
关键词
Generative adversarial networks - Embedded systems - Security systems;
D O I
10.1109/MC.2019.2924546
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Generative adversarial networks can be exploited to launch attacks against detection systems that rely on artificial intelligence (Al). To build effective cyberphysical systems that are operationally robust and socially accepted, we must expend significant effort to develop novel Al-based safety-critical systems.
引用
收藏
页码:78 / 81
页数:4
相关论文
共 13 条
[1]  
[Anonymous], P 2018 INT C BIOM IC
[2]  
[Anonymous], WHAT ARE SOME RECENT
[3]  
[Anonymous], 29 INT C NEUR INF PR
[4]  
Behzadan Vahid, 2017, Machine Learning and Data Mining in Pattern Recognition. 13th International Conference, MLDM 2017. Proceedings: LNAI 10358, P262, DOI 10.1007/978-3-319-62416-7_19
[5]   Fast Geometrically-Perturbed Adversarial Faces [J].
Dabouei, Ali ;
Soleymani, Sobhan ;
Dawson, Jeremy ;
Nasrabadi, Nasser M. .
2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, :1979-1988
[6]  
Garvie C., 2016, The Perpetual Line-Up: Unregulated Police Face Recognition in America
[7]  
Goodfellow I., PROC 27 INT C NEURAL
[8]  
Kurakin A., 2017, PROC INT C LEARN REP
[9]   Preserving privacy by de-identifying face images [J].
Newton, EM ;
Sweeney, L ;
Malin, B .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2005, 17 (02) :232-243
[10]   DeepFace: Closing the Gap to Human-Level Performance in Face Verification [J].
Taigman, Yaniv ;
Yang, Ming ;
Ranzato, Marc'Aurelio ;
Wolf, Lior .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :1701-1708