Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning

被引:114
|
作者
Phan, NhatHai [1 ]
Wu, Xintao [2 ]
Hu, Han [1 ]
Dou, Dejing [3 ]
机构
[1] New Jersey Inst Technol, Newark, NJ 07102 USA
[2] Univ Arkansas, Fayetteville, AR 72701 USA
[3] Univ Oregon, Eugene, OR 97403 USA
关键词
D O I
10.1109/ICDM.2017.48
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability to adaptively inject noise into features based on the contribution of each to the output; and (3) It could be applied in a variety of different deep neural networks. To achieve this, we figure out a way to perturb affine transformations of neurons, and loss functions used in deep neural networks. In addition, our mechanism intentionally adds "more noise" into features which are "less relevant" to the model output, and vice-versa. Our theoretical analysis further derives the sensitivities and error bounds of our mechanism. Rigorous experiments conducted on MNIST and CIFAR-10 datasets show that our mechanism is highly effective and outperforms existing solutions.
引用
收藏
页码:385 / 394
页数:10
相关论文
共 50 条
  • [41] Tempered Sigmoid Activations for Deep Learning with Differential Privacy
    Papernot, Nicolas
    Thakurta, Abhradeep
    Song, Shuang
    Chien, Steve
    Erlingsson, Ulfar
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 9312 - 9321
  • [42] Analysis of Application Examples of Differential Privacy in Deep Learning
    Shen, Zhidong
    Zhong, Ting
    COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2021, 2021
  • [43] Staircase based differential privacy with branching mechanism for location privacy preservation in wireless sensor networks
    Chakraborty, Bodhi
    Verma, Shekhar
    Singh, Krishna Pratap
    COMPUTERS & SECURITY, 2018, 77 : 36 - 48
  • [44] Maintaining Privacy in Medical Imaging with Federated Learning, Deep Learning, Differential Privacy, and Encrypted Computation
    Shah, Unnati
    Dave, Ishita
    Malde, Jeel
    Mehta, Jalpa
    Kodeboyina, Srikanth
    2021 6TH INTERNATIONAL CONFERENCE FOR CONVERGENCE IN TECHNOLOGY (I2CT), 2021,
  • [45] A Pragmatic Privacy-Preserving Deep Learning Framework Satisfying Differential Privacy
    Dang T.K.
    Tran-Truong P.T.
    SN Computer Science, 5 (1)
  • [46] An Adaptive Mechanism for Accurate Query Answering under Differential Privacy
    Li, Chao
    Miklau, Gerome
    PROCEEDINGS OF THE VLDB ENDOWMENT, 2012, 5 (06): : 514 - 525
  • [47] An efficient deep learning model for brain tumour detection with privacy preservation
    Rehman, Mujeeb Ur
    Shafique, Arslan
    Khan, Imdad Ullah
    Ghadi, Yazeed Yasin
    Ahmad, Jawad
    Alshehri, Mohammed S.
    Al Qathrady, Mimonah
    Alhaisoni, Majed
    Zayyan, Muhammad H.
    CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2023,
  • [48] Privacy Preservation Learning with Deep Cooperative Method for Multimedia Data Analysis
    Si, Wen
    Liu, Cong
    SECURITY AND COMMUNICATION NETWORKS, 2022, 2022
  • [49] Mechanism for Privacy Preservation in VANETS
    Chaurasia, Brijesh K.
    Verma, Shekhar
    Tomar, G. S.
    INTERNATIONAL JOURNAL OF GRID AND HIGH PERFORMANCE COMPUTING, 2010, 2 (02) : 12 - 22
  • [50] Aldp-fl: an adaptive local differential privacy-based federated learning mechanism for IoT
    Li, Jinguo
    Lu, Mengli
    Zhang, Jin
    Wu, Jing
    International Journal of Information Security, 2025, 24 (01)