Zihang Xiang
Research Subjects
Research Interests
Zihang Xiang has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Di Wang
Nanyang technological university, Singapore, Singapore
2 shared publications Bin Zhang
Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Kingdom of Saudi Arabia
1 shared publication- Chencheng Xu
Syneron Opal George Town Cayman Island
1 shared publication Chupeng Lu
Key Laboratory of In-Fiber Integrated Optics, Ministry Education of China, Harbin Engineering University, Harbin, China
1 shared publication- Cuiting Sun
Key Laboratory of In-Fiber Integrated Optics, Ministry Education of China, Harbin Engineering University, Harbin, China
1 shared publication - Haoyang Li
Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 2 February 2024
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 10 (5) , eadh8601
PPML-Omics: A privacy-preserving federated machine learning method protects patients’ privacy in omic data
Modern machine learning models toward various tasks with omic data analysis give rise to threats of privacy leakage of patients involved in those datasets. Here, we proposed a secure and privacy-preserving machine learning method (PPML-Omics) by designing a decentralized differential private federated learning algorithm. We applied PPML-Omics to analyze data from three sequencing technologies and addressed the privacy concern in three major tasks of omic data under three representative deep learning models. We examined privacy breaches in depth through privacy attack experiments and demonstrated that PPML-Omics could protect patients’ privacy. In each of these applications, PPML-Omics was able to outperform methods of comparison under the same level of privacy guarantee, demonstrating the versatility of the method in simultaneously balancing the privacy-preserving capability and utility in omic data analysis. Furthermore, we gave the theoretical proof of the privacy-preserving capability of PPML-Omics, suggesting the first mathematically guaranteed method with robust and generalizable empirical performance in protecting patients’ privacy in omic data.
- 2 February 2024
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 10 (5) , eadh8601
Top Cited PapersOpen AccessPPML-Omics: A privacy-preserving federated machine learning method protects patients’ privacy in omic data
Modern machine learning models toward various tasks with omic data analysis give rise to threats of privacy leakage of patients involved in those datasets. Here, we proposed a secure and privacy-preserving machine learning method (PPML-Omics) by designing a decentralized differential private federated learning algorithm. We applied PPML-Omics to analyze data from three sequencing technologies and addressed the privacy concern in three major tasks of omic data under three representative deep learning models. We examined privacy breaches in depth through privacy attack experiments and demonstrated that PPML-Omics could protect patients’ privacy. In each of these applications, PPML-Omics was able to outperform methods of comparison under the same level of privacy guarantee, demonstrating the versatility of the method in simultaneously balancing the privacy-preserving capability and utility in omic data analysis. Furthermore, we gave the theoretical proof of the privacy-preserving capability of PPML-Omics, suggesting the first mathematically guaranteed method with robust and generalizable empirical performance in protecting patients’ privacy in omic data.
- Open Access
- 13 June 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 1 (2) , 1-26
Practical Differentially Private and Byzantine-resilient Federated Learning
Privacy and Byzantine resilience are two indispensable requirements for a federated learning (FL) system. Although there have been extensive studies on privacy and Byzantine security in their own track, solutions that consider both remain sparse. This is due to difficulties in reconciling privacy-preserving and Byzantine-resilient algorithms. In this work, we propose a solution to such a two-fold issue. We use our version of differentially private stochastic gradient descent (DP-SGD) algorithm to preserve privacy and then apply our Byzantine-resilient algorithms. We note that while existing works follow this general approach, an in-depth analysis on the interplay between DP and Byzantine resilience has been ignored, leading to unsatisfactory performance. Specifically, for the random noise introduced by DP, previous works strive to reduce its seemingly detrimental impact on the Byzantine aggregation. In contrast, we leverage the random noise to construct a first-stage aggregation that effectively rejects many existing Byzantine attacks. Moreover, based on another property of our DP variant, we form a second-stage aggregation which provides a final sound filtering. Our protocol follows the principle of co-designing both DP and Byzantine resilience. We provide both theoretical proof and empirical experiments to show our protocol is effective: retaining high accuracy while preserving the DP guarantee and Byzantine resilience. Compared with the previous work, our protocol 1) achieves significantly higher accuracy even in a high privacy regime; 2) works well even when up to 90% distributive workers are Byzantine.
- 13 June 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 1 (2) , 1-26
Open AccessPractical Differentially Private and Byzantine-resilient Federated Learning
Privacy and Byzantine resilience are two indispensable requirements for a federated learning (FL) system. Although there have been extensive studies on privacy and Byzantine security in their own track, solutions that consider both remain sparse. This is due to difficulties in reconciling privacy-preserving and Byzantine-resilient algorithms. In this work, we propose a solution to such a two-fold issue. We use our version of differentially private stochastic gradient descent (DP-SGD) algorithm to preserve privacy and then apply our Byzantine-resilient algorithms. We note that while existing works follow this general approach, an in-depth analysis on the interplay between DP and Byzantine resilience has been ignored, leading to unsatisfactory performance. Specifically, for the random noise introduced by DP, previous works strive to reduce its seemingly detrimental impact on the Byzantine aggregation. In contrast, we leverage the random noise to construct a first-stage aggregation that effectively rejects many existing Byzantine attacks. Moreover, based on another property of our DP variant, we form a second-stage aggregation which provides a final sound filtering. Our protocol follows the principle of co-designing both DP and Byzantine resilience. We provide both theoretical proof and empirical experiments to show our protocol is effective: retaining high accuracy while preserving the DP guarantee and Byzantine resilience. Compared with the previous work, our protocol 1) achieves significantly higher accuracy even in a high privacy regime; 2) works well even when up to 90% distributive workers are Byzantine.
- 5 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (12) , 11756-11762
An Improved Strain Sensor Based on Long-Period Fiber Grating With a Local Ellipse-Core Structure
In this paper, we proposed a novel long-period fiber grating strain sensor based on local ellipse-core fiber (LEC-LPFG). The LEC-LPFG was fabricated by laser polishing and local heating methods, which could efficiently transform a single-mode fiber (SMF) into a periodic ellipse-core fiber. The effects associated with the fiber elliptical core shape were shown to significantly influence the strain sensitivity of the LEC-LPFG. Further, it was demonstrated that the LEC-LPFG has a high strain sensitivity of −20.2 pm/ $\mu \varepsilon $ and a temperature sensitivity of 68.6 pm/°C. Our work provides a new technology for straightforward, low-cost, and large-scale productions of premium fiber optical strain sensors which are desirable in many practical applications.
- 5 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (12) , 11756-11762
An Improved Strain Sensor Based on Long-Period Fiber Grating With a Local Ellipse-Core Structure
In this paper, we proposed a novel long-period fiber grating strain sensor based on local ellipse-core fiber (LEC-LPFG). The LEC-LPFG was fabricated by laser polishing and local heating methods, which could efficiently transform a single-mode fiber (SMF) into a periodic ellipse-core fiber. The effects associated with the fiber elliptical core shape were shown to significantly influence the strain sensitivity of the LEC-LPFG. Further, it was demonstrated that the LEC-LPFG has a high strain sensitivity of −20.2 pm/ $\mu \varepsilon $ and a temperature sensitivity of 68.6 pm/°C. Our work provides a new technology for straightforward, low-cost, and large-scale productions of premium fiber optical strain sensors which are desirable in many practical applications.