PrivColl: Practical Privacy-Preserving Collaborative Machine Learning

Zhang, Yanjun; Bai, Guangdong; Li, Xue; Curtis, Caitlin; Chen, Chen; Ko, Ryan K. L.

doi:10.1007/978-3-030-58951-6_20

Cited by 28 publications

(32 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secure aggregation typically employs cryptographic mechanisms such as homomorphic encryption (HE) [7,31,40] and/or secure multiparty computation (MPC) [4,10,11,30,34,47] to securely evaluate the gradient ∇𝐹 (𝑤 𝑘 , 𝜉 𝑙,𝑘 ) without revealing local data. With ∇𝐹 (𝑤 𝑘 , 𝜉 𝑙,𝑘 ), all the participants can thus take a gradient descent step by Equation 2.…”

Section: Secure Aggregationmentioning

confidence: 99%

“…In the traditional FL, every participant owns its local training dataset, and updates the same global model 𝑤 𝑘 via a parameter server using its local model/gradients. The local gradients ∇𝐹 (𝑤 𝑘 , 𝜉 𝑙,𝑘 ) can be protected via either secure aggregation [4,30,31,34,40,47] or differential privacy mechanisms [2,8,21,42,44,48]. This process can be decentralized by replacing the parameter server with a peer-to-peer communication mechanism [22,39].…”

Section: Cgd Optimizationmentioning

confidence: 99%

“…The sharing of local parameters/gradients is subject to model inversion attack [9,32,43] . Privacy-preserving SGD via secure aggregation [4,30,31,34,40,47] As above, since the mechanism guarantees that the computation result from ciphertext is the same from plaintext [4,34].…”

Section: Cgd Optimizationmentioning

confidence: 99%

“…𝑔 𝑗 (𝑤 𝑗 𝑘 , 𝜉 𝑗 ). A straightforward way is to let each participant release its local gradient 𝑔 𝑙 (𝑤 𝑙 𝑘 , 𝜉 𝑙 ), but it may leak information about 𝜉 𝑙 or 𝑤 𝑙 𝑘 [47]. To address this, we incorporate the secure addition operation [3,4,29,45] on the local gradients to calculate their sum without releasing each of them.…”

Section: 𝑚 𝑗=1mentioning

confidence: 99%

“…This has been proved to be viable through the additive secret sharing scheme, in which the sum of a set of secret values is collaboratively calculated without revealing any addends [3,4,29,45]. A previous study [47] demonstrates it is efficient when applied to achieve decentralization in FL. We prove that the adversary's observation in CGD is only the sum of local gradients, and it conceals the extra indicative information that traditional FL would leak (cf.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Confined Gradient Descent: Privacy-preserving Optimization for Federated Learning

Zhang,

Bai,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Federated learning enables multiple participants to collaboratively train a model without aggregating the training data. Although the training data are kept within each participant and the local gradients can be securely synthesized, recent studies have shown that such privacy protection is insufficient. The global model parameters that have to be shared for optimization are susceptible to leak information about training data. In this work, we propose Confined Gradient Descent (CGD) that enhances privacy of federated learning by eliminating the sharing of global model parameters. CGD exploits the fact that a gradient descent optimization can start with a set of discrete points and converges to another set at the neighborhood of the global minimum of the objective function. It lets the participants independently train on their local data, and securely share the sum of local gradients to benefit each other. We formally demonstrate CGD 's privacy enhancement over traditional FL. We prove that less information is exposed in CGD compared to that of traditional FL. CGD also guarantees desired model accuracy. We theoretically establish a convergence rate for CGD. We prove that the loss of the proprietary models learned for each participant against a model learned by aggregated training data is bounded. Extensive experimental results on two real-world datasets demonstrate the performance of CGD is comparable with the centralized learning, with marginal differences on validation loss (mostly within 0.05) and accuracy (mostly within 1%).

show abstract

Section: Secure Aggregationmentioning

confidence: 99%

Section: Cgd Optimizationmentioning

confidence: 99%

Section: Cgd Optimizationmentioning

confidence: 99%

Section: 𝑚 𝑗=1mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Confined Gradient Descent: Privacy-preserving Optimization for Federated Learning

Zhang,

Bai,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

PPCNN: An efficient privacy‐preserving CNN training and inference framework

Zhao

Wang

2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Convolutional neural network (CNN) is one of the representative models of deep learning, commonly used to analyze visual images. CNN model is more accurate when trained on large amounts of data from multiple sources, and the huge training cost makes the model much more valuable. However, data from various sources is often privacy‐sensitive. Therefore, the privacy of these data should be protected during CNN model training and inference. In this paper, we propose an efficient and secure two‐party computation (2PC) framework PPCNN for privacy‐preserving CNN training and inference. Specifically, we use a new secret sharing technique introduced in ABY2.0 to securely compute various computational tasks involved in the CNN training and inference processes. This secret sharing technique can significantly reduce the communication overhead. Meanwhile, we assign these computationally intensive tasks to cloud servers to reduce the computational burden on local devices. We demonstrate the security of these protocols in the semihonest model. In addition, we use the MP‐SPDZ library to simulate our PPCNN framework, and the experiments prove its high efficiency and accuracy.

show abstract

Privacy-Preserving Gradient Descent for Distributed Genome-Wide Analysis

Zhang

Bai

et al. 2021

Computer Security – ESORICS 2021

Self Cite

View full text Add to dashboard Cite

As COVID-19 has been spreading across the world since early 2020, a growing number of malicious campaigns are capitalizing the topic of COVID-19. COVID-19 themed cryptocurrency scams are increasingly popular during the pandemic. However, these newly emerging scams are poorly understood by our community. In this paper, we present the first measurement study of COVID-19 themed cryptocurrency scams. We first create a comprehensive taxonomy of COVID-19 scams by manually analyzing the existing scams reported by users from online resources. Then, we propose a hybrid approach to perform the investigation by: 1) collecting reported scams in the wild; and 2) detecting undisclosed ones based on information collected from suspicious entities (e.g., domains, tweets, etc). We have collected 195 confirmed COVID-19 cryptocurrency scams in total, including 91 token scams, 19 giveaway scams, 9 blackmail scams, 14 crypto malware scams, 9 Ponzi scheme scams, and 53 donation scams. We then identified over 200 blockchain addresses associated with these scams, which lead to at least 330K US dollars in losses from 6,329 victims. For each type of scams, we further investigated the tricks and social engineering techniques they used. To facilitate future research, we have released all the well-labelled scams to the research community.

show abstract

PrivColl: Practical Privacy-Preserving Collaborative Machine Learning

Cited by 28 publications

References 36 publications

Confined Gradient Descent: Privacy-preserving Optimization for Federated Learning

Confined Gradient Descent: Privacy-preserving Optimization for Federated Learning

PPCNN: An efficient privacy‐preserving CNN training and inference framework

Privacy-Preserving Gradient Descent for Distributed Genome-Wide Analysis

Contact Info

Product

Resources

About