Yonghui Xiao

Yonghui Xiao

Auto-generated profile, based on publicly available information

Yonghui Xiao

Google Inc

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 December 2019 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YCYang Cao
Yang Cao
YXYonghui Xiao
Yonghui Xiao
LXLi Xiong
Li Xiong
LBLiquan Bai
Liquan Bai
MYMasatoshi Yoshikawa
Masatoshi Yoshikawa
Location privacy-preserving mechanisms (LPPMs) have been extensively studied for protecting users' location privacy by releasing a perturbed location to third parties such as location-based service providers. However, when a user's perturbed locations are released continuously, existing LPPMs may not protect the sensitive information about the user's real-world activities, such as "visited hospital in the last week" or "regularly commuting between Address 1 and 2" (it is easy to infer that Addresses 1 and 2 may be home and office), which we call it spatiotemporal event. In this paper, we first formally define spatiotemporal event as Boolean expressions between location and time predicates, and then we define $\epsilon$ -spatiotemporal event privacy by extending the notion of differential privacy. Second, to understand how much spatiotemporal event privacy that existing LPPMs can provide, we design computationally efficient algorithms to quantify the privacy leakage of state-of-the-art LPPMs when an adversary has prior knowledge of the user's initial probability over possible locations. It turns out that the existing LPPMs cannot adequately protect spatiotemporal event privacy. Third, we propose a framework, PriSTE, to transform an existing LPPM into one protecting spatiotemporal event privacy against adversaries with any prior knowledge. Our experiments on real-life and synthetic data verified that the proposed method is effective and efficient.

1 August 2019 in Proceedings of the VLDB Endowment
Verified
Journal Article
Open access
YCYang Cao
Yang Cao
YXYonghui Xiao
Yonghui Xiao
LXLi Xiong
Li Xiong
LBLiquan Bai
Liquan Bai
MYMasatoshi Yoshikawa
Masatoshi Yoshikawa
Location privacy-preserving mechanisms (LPPMs) have been extensively studied for protecting a user's location in location-based services. However, when user's perturbed locations are released continuously, existing LPPMs may not protect users' sensitive spatiotemporal event , such as "visited hospital in the last week" or "regularly commuting between location 1 and location 2 every morning and afternoon" (it is easy to infer that locations 1 and 2 may be home and office). In this demonstration, we demonstrate PriSTE for protecting spatiotemporal event privacy in continuous location release. First, to raise users' awareness of such a new privacy goal, we design an interactive tool to demonstrate how accurate an adversary could infer a secret spatiotemporal event from a sequence of locations or even LPPM-protected locations. The attendees can find that some spatiotemporal events are quite risky and even these state-of-the-art LPPMs do not always protect spatiotemporal event privacy. Second, we demonstrate how a user can use PriSTE to automatically or manually convert an LPPM for location privacy into one protecting spatiotemporal event privacy in continuous location-based services. Finally, we visualize the trade-off between privacy and utility so that users can choose appropriate privacy parameters in different application scenarios.

1 August 2018 in Proceedings of the VLDB Endowment
Verified
Journal Article
Open access
YCYang Cao
Yang Cao
LXLi Xiong
Li Xiong
MYMasatoshi Yoshikawa
Masatoshi Yoshikawa
YXYonghui Xiao
Yonghui Xiao
SZSi Zhang
Si Zhang
In many real-world systems, such as Internet of Thing, sensitive data streams are collected and analyzed continually. To protect privacy, a number of mechanisms are designed to achieve ϵ-differential privacy for processing sensitive streaming data, whose privacy loss is considered to be rigorously controlled within a given parameter ϵ. However, most of the existing studies do not consider the effect of temporal correlations among the continuously generated data on the privacy loss. Our recent work reveals that, the privacy loss of a traditional DP mechanism (e.g., Laplace mechanism) may not be bounded by ϵ due to temporal correlations. We call such unexpected privacy loss Temporal Privacy Leakage (TPL). In this demonstration, we design a system, ConTPL, which is able to automatically convert an existing differentially private streaming data release mechanism into one bounding TPL within a specified level. ConTPL also provides an interactive interface and real-time visualization to help data curator to understand and explore the effect of different parameters on TPL.

14 September 2022 in arXiv
Verified
Preprint
Open access
PDF file
Rongmei LinRongmei Lin
Rongmei Lin
YXYonghui Xiao
Yonghui Xiao
TYTien-Ju Yang
Tien-Ju Yang
DZDing Zhao
Ding Zhao
LXLi Xiong
Li Xiong
FBFrançoise Beaufays
Françoise Beaufays
Automatic Speech Recognition models require large amount of speech data for training, and the collection of such data often leads to privacy concerns. Federated learning has been widely used and is considered to be an effective decentralized technique by collaboratively learning a shared prediction model while keeping the data local on different clients devices. However, the limited computation and communication resources on clients devices present practical difficulties for large models. To overcome such challenges, we propose Federated Pruning to train a reduced model under the federated setting, while maintaining similar performance compared to the full model. Moreover, the vast amount of clients data can also be leveraged to improve the pruning results compared to centralized training. We explore different pruning schemes and provide empirical evidence of the effectiveness of our methods.

16 May 2020 in arXiv
Verified
Preprint
Open access
PDF file
YCYang Cao
Yang Cao
YXYonghui Xiao
Yonghui Xiao
LXLi Xiong
Li Xiong
LBLiquan Bai
Liquan Bai
MYMasatoshi Yoshikawa
Masatoshi Yoshikawa
Location privacy-preserving mechanisms (LPPMs) have been extensively studied for protecting users' location privacy by releasing a perturbed location to third parties such as location-based service providers. However, when a user's perturbed locations are released continuously, existing LPPMs may not protect the sensitive information about the user's spatiotemporal activities, such as "visited hospital in the last week" or "regularly commuting between Address 1 and Address 2" (it is easy to infer that Addresses 1 and 2 may be home and office), which we call it \textit{spatiotemporal event}. In this paper, we first formally define {spatiotemporal event} as Boolean expressions between location and time predicates, and then we define $ \epsilon $-\textit{spatiotemporal event privacy} by extending the notion of differential privacy. Second, to understand how much spatiotemporal event privacy that existing LPPMs can provide, we design computationally efficient algorithms to quantify the privacy leakage of state-of-the-art LPPMs when an adversary has prior knowledge of the user's initial probability over possible locations. It turns out that the existing LPPMs cannot adequately protect spatiotemporal event privacy. Third, we propose a framework, PriSTE, to transform an existing LPPM into one protecting spatiotemporal event privacy against adversaries with \textit{any} prior knowledge. Our experiments on real-life and synthetic data verified that the proposed method is effective and efficient.