differential privacy
Recently Published Documents


TOTAL DOCUMENTS

1585
(FIVE YEARS 1287)

H-INDEX

44
(FIVE YEARS 21)

2022 ◽  
Vol 22 (3) ◽  
pp. 1-22
Author(s):  
Yi Liu ◽  
Ruihui Zhao ◽  
Jiawen Kang ◽  
Abdulsalam Yassine ◽  
Dusit Niyato ◽  
...  

Federated Edge Learning (FEL) allows edge nodes to train a global deep learning model collaboratively for edge computing in the Industrial Internet of Things (IIoT), which significantly promotes the development of Industrial 4.0. However, FEL faces two critical challenges: communication overhead and data privacy. FEL suffers from expensive communication overhead when training large-scale multi-node models. Furthermore, due to the vulnerability of FEL to gradient leakage and label-flipping attacks, the training process of the global model is easily compromised by adversaries. To address these challenges, we propose a communication-efficient and privacy-enhanced asynchronous FEL framework for edge computing in IIoT. First, we introduce an asynchronous model update scheme to reduce the computation time that edge nodes wait for global model aggregation. Second, we propose an asynchronous local differential privacy mechanism, which improves communication efficiency and mitigates gradient leakage attacks by adding well-designed noise to the gradients of edge nodes. Third, we design a cloud-side malicious node detection mechanism to detect malicious nodes by testing the local model quality. Such a mechanism can avoid malicious nodes participating in training to mitigate label-flipping attacks. Extensive experimental studies on two real-world datasets demonstrate that the proposed framework can not only improve communication efficiency but also mitigate malicious attacks while its accuracy is comparable to traditional FEL frameworks.


2022 ◽  
Vol 16 (4) ◽  
pp. 1-21
Author(s):  
Honghui Xu ◽  
Zhipeng Cai ◽  
Wei Li

Multi-label image recognition has been an indispensable fundamental component for many real computer vision applications. However, a severe threat of privacy leakage in multi-label image recognition has been overlooked by existing studies. To fill this gap, two privacy-preserving models, Privacy-Preserving Multi-label Graph Convolutional Networks (P2-ML-GCN) and Robust P2-ML-GCN (RP2-ML-GCN), are developed in this article, where differential privacy mechanism is implemented on the model’s outputs so as to defend black-box attack and avoid large aggregated noise simultaneously. In particular, a regularization term is exploited in the loss function of RP2-ML-GCN to increase the model prediction accuracy and robustness. After that, a proper differential privacy mechanism is designed with the intention of decreasing the bias of loss function in P2-ML-GCN and increasing prediction accuracy. Besides, we analyze that a bounded global sensitivity can mitigate excessive noise’s side effect and obtain a performance improvement for multi-label image recognition in our models. Theoretical proof shows that our two models can guarantee differential privacy for model’s outputs, weights and input features while preserving model robustness. Finally, comprehensive experiments are conducted to validate the advantages of our proposed models, including the implementation of differential privacy on model’s outputs, the incorporation of regularization term into loss function, and the adoption of bounded global sensitivity for multi-label image recognition.


2022 ◽  
Vol 27 (2) ◽  
pp. 235-243
Author(s):  
Xu Zheng ◽  
Lizong Zhang ◽  
Kaiyang Li ◽  
Xi Zeng

2022 ◽  
Vol 127 ◽  
pp. 362-372
Author(s):  
Xiang Wu ◽  
Yongting Zhang ◽  
Minyu Shi ◽  
Pei Li ◽  
Ruirui Li ◽  
...  

2022 ◽  
Vol 23 (1) ◽  
pp. 1-42
Author(s):  
Gilles Barthe ◽  
Charlie Jacomme ◽  
Steve Kremer

We study decidability problems for equivalence of probabilistic programs for a core probabilistic programming language over finite fields of fixed characteristic. The programming language supports uniform sampling, addition, multiplication, and conditionals and thus is sufficiently expressive to encode Boolean and arithmetic circuits. We consider two variants of equivalence: The first one considers an interpretation over the finite field F q , while the second one, which we call universal equivalence, verifies equivalence over all extensions F q k of F q . The universal variant typically arises in provable cryptography when one wishes to prove equivalence for any length of bitstrings, i.e., elements of F 2 k for any k . While the first problem is obviously decidable, we establish its exact complexity, which lies in the counting hierarchy. To show decidability and a doubly exponential upper bound of the universal variant, we rely on results from algorithmic number theory and the possibility to compare local zeta functions associated to given polynomials. We then devise a general way to draw links between the universal probabilistic problems and widely studied problems on linear recurrence sequences. Finally, we study several variants of the equivalence problem, including a problem we call majority, motivated by differential privacy. We also define and provide some insights about program indistinguishability, proving that it is decidable for programs always returning 0 or 1.


2022 ◽  
Vol 2022 ◽  
pp. 1-9
Author(s):  
Jiawen Du ◽  
Yong Pi

With the advent of the era of big data, people’s lives have undergone earth-shaking changes, not only getting rid of the cumbersome traditional data collection but also collecting and sorting information directly from people’s footprints on social networks. This paper explores and analyzes the privacy issues in current social networks and puts forward the protection strategies of users’ privacy data based on data mining algorithms so as to truly ensure that users’ privacy in social networks will not be illegally infringed in the era of big data. The data mining algorithm proposed in this paper can protect the user’s identity from being identified and the user’s private information from being leaked. Using differential privacy protection methods in social networks can effectively protect users’ privacy information in data publishing and data mining. Therefore, it is of great significance to study data publishing, data mining methods based on differential privacy protection, and their application in social networks.


2022 ◽  
Vol 2022 ◽  
pp. 1-18
Author(s):  
Zhejian Zhang

As one of the cores of data analysis in large social networks, community detection has become a hot research topic in recent years. However, user’s real social relationship may be at risk of privacy leakage and threatened by inference attacks because of the semitrusted server. As a result, community detection in social graphs under local differential privacy has gradually aroused the interest of industry and academia. On the one hand, the distortion of user’s real data caused by existing privacy-preserving mechanisms can have a serious impact on the mining process of densely connected local graph structure, resulting in low utility of the final community division. On the other hand, private community detection requires to use the results of multiple user-server interactions to adjust user’s partition, which inevitably leads to excessive allocation of privacy budget and large error of perturbed data. For these reasons, a new community detection method based on the local differential privacy model (named LDPCD) is proposed in this paper. Due to the introduction of truncated Laplace mechanism, the accuracy of user perturbation data is improved. In addition, the community divisive algorithm based on extremal optimization (EO) is also refined to reduce the number of interactions between users and the server. Thus, the total privacy overhead is reduced and strong privacy protection is guaranteed. Finally, LDPCD is applied in two commonly used real-world datasets, and its advantage is experimentally validated compared with two state-of-the-art methods.


2022 ◽  
Vol 13 (1) ◽  
Author(s):  
Aleix Bassolas ◽  
Hugo Barbosa-Filho ◽  
Brian Dickinson ◽  
Xerxes Dotiwalla ◽  
Paul Eastham ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document