Querying little is enough: Model inversion attack via latent information

Kanghua Mo; Xiaozhang Liu; Teng Huang; Anli Yan

doi:10.1002/int.22315

journal article Oct 29, 2020

Querying little is enough: Model inversion attack via latent information

Kanghua Mo

Xiaozhang Liu Teng Huang

Anli Yan

International Journal of Intelligent Systems Vol. 36 No. 2 pp. 681-690 · Wiley

View at Publisher Save 10.1002/int.22315

Topics

No keywords indexed for this article. Browse by subject →

References

22

[1]

Apple. Arfaceanchor.blendshapelocation.https://developer.apple.com/. Accessed October 1 2020.

[2]

Amazon. Machine learning at AWS.https://aws.amazon.com/machine-learning/. Accessed October 1 2020.

[3]

Tencent. Facerecognition.https://cloud.tencent.com/product/. Accessed October 1 2020.

[4]

FredriksonM JhaS RistenpartT. Model inversion attacks that exploit confidence information and basic counter measures. In Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security; 2015:1322‐1333. 10.1145/2810103.2813677

[5]

Várkonyi‐Kóczy AR (2009) 10.1007/978-3-642-03737-5_49

[6]

MahendranA VedaldiA.Understanding deep image representations by inverting them. In2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2015:5188‐5196. 10.1109/cvpr.2015.7299155

[7]

DosovitskiyA BroxT.Inverting visual representations with convolutional networks. In2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016:4829‐4837. 10.1109/cvpr.2016.522

[8]

NashC KushmanN WilliamsCKI.Inverting supervised representations with autoregressive neural density models. InThe 22nd International Conference on Artificial Intelligence and Statistics; 2018;1620‐1629.

[9]

YangZ ZhangJ ChangEC LiangZ.Neural network inversion in adversarial setting via background knowledge alignment. InCCS '19 Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security; 2019:225‐240. 10.1145/3319535.3354261

[10]

Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

Aude Oliva, Antonio Torralba

International Journal of Computer Vision 10.1023/a:1011139631724

[11]

Distinctive Image Features from Scale-Invariant Keypoints

David G. Lowe

International Journal of Computer Vision 10.1023/b:visi.0000029664.99615.94

[12]

Histograms of Oriented Gradients for Human Detection

N. Dalal, B. Triggs

2005 IEEE Computer Society Conference on Computer... 10.1109/cvpr.2005.177

[13]

OquabM BottouL LaptevI SivicJ.Learning and transferring mid‐level image representations using convolutional neural networks. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2014:1717‐1724. 10.1109/cvpr.2014.222

[14]

WeiY XiaW HuangJ.et al. Cnn: Single‐label to multi‐label book title: CoRR. arXiv preprint arXiv:1406.5726 2014.

[15]

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan et al.

2014 IEEE Conference on Computer Vision and Patter... 10.1109/cvprw.2014.131

[16]

ImageNet classification with deep convolutional neural networks

Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton

Communications of the ACM 10.1145/3065386

[17]

SimonyanK ZissermanA.Very deep convolutional networks for large‐scale image recognition. InICLR 2015: International Conference on Learning Representations 2015; 2015.

[18]

Deep Residual Learning for Image Recognition

Kaiming He, Xiangyu Zhang, Shaoqing Ren et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.90

[19]

LeCunY. The MNIST database of handwritten digits [published online ahead of print October 1 2020]. 1998.http://yann.lecun.com/exdb/mnist/. Accessed October 1 2020.

[20]

KumarN BergAC BelhumeurPN NayarSK. Attribute and simile classifiers for face verification. In2009 IEEE 12th International Conference on Computer Vision. IEEE; 2009:365‐372. 10.1109/iccv.2009.5459250

[21]

HuangGB MattarM BergT Learned‐MillerE.2008. Labeled faces in the wild: A database for studying face recognition in unconstrained environments.

[22]

ZhangT.Solving large scale linear prediction problems using stochastic gradient descent algorithms. InProceedings of the Twenty‐first International Conference on Machine Learning. 2004;116. 10.1145/1015330.1015332

Metrics

18

Citations

22

References

Details

Published: Oct 29, 2020
Vol/Issue: 36(2)
Pages: 681-690
License: View

Authors

K

Kanghua Mo

School of Computer Science & Cyberspace Security Hainan University Haikou China; Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou China

X

Xiaozhang Liu

School of Computer Science & Cyberspace Security Hainan University Haikou China

T

Teng Huang

Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou China

A

Anli Yan

School of Computer Science & Cyberspace Security Hainan University Haikou China

Cite This Article

Kanghua Mo, Xiaozhang Liu, Teng Huang, et al. (2020). Querying little is enough: Model inversion attack via latent information. International Journal of Intelligent Systems, 36(2), 681-690. https://doi.org/10.1002/int.22315

Querying little is enough: Model inversion attack via latent information

You May Also Like