利用化妝攻擊對人臉辨識系統生成對抗範例;Generating Adversarial Examples by Makeup Attacks on Face Recognition

National Chung Cheng University Institutional Repository > 工學院 > 資訊工程學系 > 學位論文 > Item A095B0000Q/54

Please use this identifier to cite or link to this item: http://ccur.lib.ccu.edu.tw/handle/A095B0000Q/54

Title:	利用化妝攻擊對人臉辨識系統生成對抗範例;Generating Adversarial Examples by Makeup Attacks on Face Recognition
Authors:	盧允中;LU, YUN-ZHONG
Contributors:	資訊工程研究所
Keywords:	深度學習;生成對抗網路;對抗性攻擊;Deep learning;Generative Adversarial Networks;Adversarial Examples
Date:	2018
Issue Date:	2019-05-23 10:30:18 (UTC+8)
Publisher:	資訊工程研究所
Abstract:	機器學習的發展非常迅速，在電腦視覺和自然語言處理方面都有很好的成果。有許多深度學習技術被運用在人類日常生活當中例如自動駕駛汽車和人臉辨識系統。如今，人類日常生活漸漸的依賴於深度神經網路可能會導致嚴重的後果，因此神經網路的安全性就變的很重要。因此展現深度神經網路其實有明顯的弱點，我們提出了一種基於生成對抗網絡的方法來生成可以欺騙人臉識別系統的臉部化妝圖片。我們在人類無法察覺的異常化妝照片結果中隱藏了攻擊的擾動信息。實驗結果顯示，我們不但可以生成高畫質的臉部化妝圖像，並且我們的攻擊結果在人臉識別系統中具有很高的攻擊成功率。 Machine Learning has developed rapidly, and has achieve great success in computer vision and natural language processing. Many machine learning technologies are used in human daily life, such as self-driving car and face recognition system. Nowadays, human are really reliance on deep neural networks (DNNs), and if the DNNs has been attacked it will cause terrible results. In order to show the vulnerable of DNNs we propose a method based on Generative Adversarial Networks (GANs) to generate face makeup image that can fooling face recognition system. We hide the perturbation information of attack in the results of the makeup photos that undetectable to human. The experiment results show that we can generate high quality face makeup image and our attack results have high success rate on face recognition system.
Appears in Collections:	[資訊工程學系] 學位論文

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	421	View/Open

Loading...