Safe Fakes: Evaluating Face Anonymizers for Face Detectors

计算机科学 探测器 面子(社会学概念) 人工智能 面部识别系统 训练集 生成对抗网络 人脸检测 模式识别(心理学) 深度学习 计算机视觉 社会科学 电信 社会学
作者
Sander R. Klomp,Matthew van Rijn,Rob G. J. Wijnhoven,Cees G. M. Snoek,Peter H. N. de With
标识
DOI:10.1109/fg52635.2021.9666936
摘要

Since the introduction of the GDPR and CCPA privacy legislation, both public and private facial image datasets are increasingly scrutinized. Several datasets have been taken offline completely and some have been anonymized. However, it is unclear how anonymization impacts face detection performance. To our knowledge, this paper presents the first empirical study on the effect of image anonymization on supervised training of face detectors. We compare conventional face anonymiz-ers with three state-of-the-art Generative Adversarial Network-based (GAN) methods, by training an off-the-shelf face detector on anonymized data. Our experiments investigate the suitability of anonymization methods for maintaining face detector performance, the effect of detectors overtraining on anonymization artefacts, dataset size for training an anonymizer, and the effect of training time of anonymization GANs. A final experiment investigates the correlation between common GAN evaluation metrics and the performance of a trained face detector. Although all tested anonymization methods lower the performance of trained face detectors, faces anonymized using GANs cause far smaller performance degradation than conventional methods. As the most important finding, the best-performing GAN, DeepPrivacy, removes identifiable faces for a face detector trained on anonymized data, resulting in a modest decrease from 91.0 to 88.3 mAP. In the last few years, there have been rapid improvements in realism of GAN-generated faces. We expect that further progression in GAN research will allow the use of Deep Fake technology for privacy-preserving Safe Fakes, without any performance degradation for training face detectors.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
kk完成签到,获得积分10
1秒前
WILL完成签到,获得积分10
1秒前
1秒前
善学以致用应助黄晟钊采纳,获得10
2秒前
啦咯是吗发布了新的文献求助10
2秒前
Albert完成签到,获得积分10
2秒前
3秒前
山海完成签到,获得积分10
3秒前
222发布了新的文献求助10
3秒前
善良应助科研通管家采纳,获得10
4秒前
怎么说应助科研通管家采纳,获得10
4秒前
今后应助科研通管家采纳,获得10
4秒前
lelelele完成签到,获得积分10
4秒前
4秒前
沐颜完成签到,获得积分10
4秒前
深情安青应助科研通管家采纳,获得10
4秒前
CodeCraft应助科研通管家采纳,获得10
4秒前
pluto应助科研通管家采纳,获得10
4秒前
JamesPei应助科研通管家采纳,获得10
4秒前
5秒前
SciGPT应助科研通管家采纳,获得10
5秒前
5秒前
科研通AI2S应助WYT采纳,获得10
5秒前
5秒前
5秒前
柯一一应助WYT采纳,获得10
5秒前
5秒前
5秒前
carrie发布了新的文献求助10
5秒前
5秒前
没有香菜完成签到,获得积分10
5秒前
6秒前
明小丽完成签到,获得积分10
6秒前
羽羽发布了新的文献求助10
6秒前
七叶树完成签到,获得积分10
7秒前
执着的紫完成签到,获得积分10
8秒前
orange完成签到,获得积分10
8秒前
Crystal发布了新的文献求助10
8秒前
8秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968934
求助须知:如何正确求助?哪些是违规求助? 3513835
关于积分的说明 11170238
捐赠科研通 3249167
什么是DOI,文献DOI怎么找? 1794650
邀请新用户注册赠送积分活动 875278
科研通“疑难数据库(出版商)”最低求助积分说明 804755