Deep Domain Adaptation With Differential Privacy

Wang, Qian; Zi-xi, LI; Zou, Qin; Zhao, Lingchen; Wang, Song

doi:10.1109/tifs.2020.2983254

Cited by 22 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tis framework establishes the sensitivity of the DP mechanism. DPDA [39] adds Gaussian noise to specifc layers and corresponding gradients to achieve (ϵ, δ)-DP while using an adversarial learning strategy to obtain domain-invariant features for the classifcation of unlabeled target domain data.…”

Section: Diferentially Private Transfermentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Domain Adaptation with Differentially Private Gradient Projection

Zheng

Zhang

2023

International Journal of Intelligent Systems

View full text Add to dashboard Cite

Domain adaptation is a viable solution for deep learning with small data. However, domain adaptation models trained on data with sensitive information may be a violation of personal privacy. In this article, we proposed a solution for unsupervised domain adaptation, called DP-CUDA, which is based on differentially private gradient projection and contradistinguisher. Compared with the traditional domain adaptation process, DP-CUDA involves searching for domain-invariant features between the source domain and target domain first and then transferring knowledge. Specifically, the model is trained in the source domain by supervised learning from labeled data. During the training of the target model, feature learning is used to solve the classification task in an end-to-end manner using unlabeled data directly, and the differentially private noise is injected into the gradient. We conducted extensive experiments on a variety of benchmark datasets, including MNIST, USPS, SVHN, VisDA-2017, Office-31, and Amazon Review, to demonstrate our proposed method’s utility and privacy-preserving properties.

show abstract

Section: Diferentially Private Transfermentioning

confidence: 99%

“…On these datasets, we consider the eight main DA tasks that have been studied [15,16,39]. Te following are eight visual tasks and data processing settings, In the three domains, the image resolutions are diferent.…”

Section: Visual Damentioning

confidence: 99%

Unsupervised Domain Adaptation with Differentially Private Gradient Projection

Zheng

Zhang

2023

International Journal of Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…Therefore, it is interesting to investigate the performance of multimodal personality trait recognition methods in cross-data set environment. To address this issue, deep domain adaption methods (Wang et al, 2020;Kurmi et al, 2021;Shao and Zhong, 2021) may be an alternative. Note that the display of personality traits and the traits themself can be considered as context-dependent.…”

Section: Personality Trait Recognition Data Setsmentioning

confidence: 99%

Deep Personality Trait Recognition: A Survey

2022

View full text Add to dashboard Cite

Automatic personality trait recognition has attracted increasing interest in psychology, neuropsychology, and computer science, etc. Motivated by the great success of deep learning methods in various tasks, a variety of deep neural networks have increasingly been employed to learn high-level feature representations for automatic personality trait recognition. This paper systematically presents a comprehensive survey on existing personality trait recognition methods from a computational perspective. Initially, we provide available personality trait data sets in the literature. Then, we review the principles and recent advances of typical deep learning techniques, including deep belief networks (DBNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). Next, we describe the details of state-of-the-art personality trait recognition methods with specific focus on hand-crafted and deep learning-based feature extraction. These methods are analyzed and summarized in both single modality and multiple modalities, such as audio, visual, text, and physiological signals. Finally, we analyze the challenges and opportunities in this field and point out its future directions.

show abstract

“…[26] proposed randomizing the shared local model weights to protect from gradient leakage attack. [51] performed domain adaptation in an adversarial-training manner. However, [33] has shown that although adversarial training can make it difficult for the adversary to recover the input data, it cannot entirely remove the sensitive information from the data representations.…”

Section: Domain Adaptation With Privacy Concernmentioning

confidence: 99%

A Privacy-Preserving Unsupervised Domain Adaptation Framework for Clinical Text Analysis

An¹,

Li²,

Gu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep Domain Adaptation With Differential Privacy

Cited by 22 publications

References 35 publications

Unsupervised Domain Adaptation with Differentially Private Gradient Projection

Unsupervised Domain Adaptation with Differentially Private Gradient Projection

Deep Personality Trait Recognition: A Survey

A Privacy-Preserving Unsupervised Domain Adaptation Framework for Clinical Text Analysis

Contact Info

Product

Resources

About