Open AccessDeceiving Face Recognition Neural Network with Samples Generated by Deepfool
Author(s) -
Jingsong Xue,
Yang Yu,
Dongsheng Jing
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1302/2/022059
Subject(s) - computer science , face (sociological concept) , facial recognition system , adversarial system , artificial intelligence , authentication (law) , artificial neural network , field (mathematics) , identity (music) , deception , pattern recognition (psychology) , machine learning , image (mathematics) , euclidean distance , convolutional neural network , deep learning , computer security , mathematics , law , social science , physics , sociology , acoustics , pure mathematics , political science
Image-based identity authentication systems have been extensively used recently. However, it holds the risk of illegal use of the images for authentication by others, which will cause a severe threat to personal privacy and security protection. The concept of adversarial samples, which is often utilized in the field of deep learning to deceive classification models, has become more and more popular, and has accumulated lots of significant efforts. Meanwhile, previous work mainly focused on interpreting images by features rather than by the structural characteritics of the human face, which made the deception of face recognition model ineffective. To solve the problem, face recognition neural network deceiving method that is based on Deepfool algorithm is proposed. For a specific face recognition neural network, white-box attack is used to generate adversarial samples, and Euclidean distance is utilized to optimize adversarial samples to obtain face photos with misleading attributes. The proposed approach can be used for privacy and security protection. Experiments on several face testing data sets verify effeteness of our proposed approach.