Search

Your search keyword '"Tian, Zhiyi"' showing total 28 results
Start Over Author "Tian, Zhiyi" Publication Year Range Last 50 years
28 results on '"Tian, Zhiyi"'

1. Machine Unlearning: A Comprehensive Survey

Author

Wang, Weiqi, Tian, Zhiyi, Zhang, Chenhan, and Yu, Shui

Subjects
Computer Science - Cryptography and Security, Computer Science - Artificial Intelligence
Abstract

As the right to be forgotten has been legislated worldwide, many studies attempt to design unlearning mechanisms to protect users' privacy when they want to leave machine learning service platforms. Specifically, machine unlearning is to make a trained model to remove the contribution of an erased subset of the training dataset. This survey aims to systematically classify a wide range of machine unlearning and discuss their differences, connections and open problems. We categorize current unlearning methods into four scenarios: centralized unlearning, distributed and irregular data unlearning, unlearning verification, and privacy and security issues in unlearning. Since centralized unlearning is the primary domain, we use two parts to introduce: firstly, we classify centralized unlearning into exact unlearning and approximate unlearning; secondly, we offer a detailed introduction to the techniques of these methods. Besides the centralized unlearning, we notice some studies about distributed and irregular data unlearning and introduce federated unlearning and graph unlearning as the two representative directions. After introducing unlearning methods, we review studies about unlearning verification. Moreover, we consider the privacy and security issues essential in machine unlearning and organize the latest related literature. Finally, we discuss the challenges of various unlearning scenarios and address the potential research directions.

Published
2024

2. A Survey on Semantic Communication Networks: Architecture, Security, and Privacy

Author

Guo, Shaolong, Wang, Yuntao, Zhang, Ning, Su, Zhou, Luan, Tom H., Tian, Zhiyi, and Shen, Xuemin

Subjects
Computer Science - Networking and Internet Architecture
Abstract

Semantic communication, emerging as a breakthrough beyond the classical Shannon paradigm, aims to convey the essential meaning of source data rather than merely focusing on precise yet content-agnostic bit transmission. By interconnecting diverse intelligent agents (e.g., autonomous vehicles and VR devices) via semantic communications, the semantic communication networks (SemComNet) supports semantic-oriented transmission, efficient spectrum utilization, and flexible networking among collaborative agents. Consequently, SemComNet stands out for enabling ever-increasing intelligent applications, such as autonomous driving and Metaverse. However, being built on a variety of cutting-edge technologies including AI and knowledge graphs, SemComNet introduces diverse brand-new and unexpected threats, which pose obstacles to its widespread development. Besides, due to the intrinsic characteristics of SemComNet in terms of heterogeneous components, autonomous intelligence, and large-scale structure, a series of critical challenges emerge in securing SemComNet. In this paper, we provide a comprehensive and up-to-date survey of SemComNet from its fundamentals, security, and privacy aspects. Specifically, we first introduce a novel three-layer architecture of SemComNet for multi-agent interaction, which comprises the control layer, semantic transmission layer, and cognitive sensing layer. Then, we discuss its working modes and enabling technologies. Afterward, based on the layered architecture of SemComNet, we outline a taxonomy of security and privacy threats, while discussing state-of-the-art defense approaches. Finally, we present future research directions, clarifying the path toward building intelligent, robust, and green SemComNet. To our knowledge, this survey is the first to comprehensively cover the fundamentals of SemComNet, alongside a detailed analysis of its security and privacy issues.

Published
2024

3. Cross-Sectional Survey of Factors Contributing to COVID-19 Testing Hesitancy Among US Adults at Risk of Severe Outcomes from COVID-19

Author

Assaf, Annlouise R., Sidhu, Gurinder S., Soni, Apurv, Cappelleri, Joseph C., Draica, Florin, Herbert, Carly, Arham, Iqra, Bader, Mehnaz, Jimenez, Camille, Bois, Michael, Silvester, Eliza, Meservey, Jessica, Eng, Valerie, Nelson, Megan, Cai, Yong, Nangarlia, Aakansha, Tian, Zhiyi, Liu, Yanping, and Watt, Stephen

Published
2024
Full Text
View/download PDF

4. Unveiling the Unseen: Video Recognition Attacks on Social Software

Author

Zhao, Hangyu, Wu, Hua, Bian, Xuqiong, Liu, Songtao, Cheng, Guang, Hu, Xiaoyan, Tian, Zhiyi, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Zhu, Tianqing, editor, and Li, Yannan, editor

Published
2024
Full Text
View/download PDF

5. GSMI: A Gradient Sign Optimization Based Model Inversion Method

Author

Tian, Zhiyi, Zhang, Chenhan, Cui, Lei, Yu, Shui, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Long, Guodong, editor, Yu, Xinghuo, editor, and Wang, Sen, editor

Published
2022
Full Text
View/download PDF

9. An Asynchronous Multi-Task Semantic Communication Method

Author

Tian, Zhiyi, Vo, Hiep, Zhang, Chenhan, Min, Geyong, and Yu, Shui

Abstract

Semantic communication has sparked great interest, due to the rising demands of emerging applications on high communication capacity and low latency. The majority of existing semantic communication methods are task-oriented, which transmit task-related semantic information via synchronous trained deep learning-based (DL-based) encoders and decoders. However, these methods have limitations in handling multi-task communications. Moreover, the synchronous training paradigm also leads to significant communication overhead in the establishing phase. In this article, we propose an asynchronous multi-task semantic communication method. In the proposed method, the DL-based encoder is trained independently using a contrastive learning method to extract task-independent semantic knowledge. Then, the receiver trains different DL-based decoders to perform various communication tasks based on the pre-trained encoder. Our method enables the accomplishment of multiple communication tasks in a single transmission. Moreover, the asynchronous training paradigm can reduce the communication overhead during the training phase of our system. The experimental results demonstrate that the proposed method achieves state-of-the-art performance in image classification and reconstruction tasks while requiring less than 10% of the training communication time compared to existing semantic communication systems.

Published
2024
Full Text
View/download PDF

10. The Role of Class Information in Model Inversion Attacks Against Image Deep Learning Classifiers

Author

Tian, Zhiyi, Cui, Lei, Zhang, Chenhan, Tan, Shuaishuai, Yu, Shui, and Tian, Yonghong

Abstract

Model inversion attacks can reconstruct the training samples of victim deep learning models. The existing efforts heavily rely on auxiliary information of the target samples (prior target information) to achieve their adversarial goals. However, prior target information is hard to obtain in practice. In this article, we explore the effect of class information in model inversion attacks to reduce the reliance of prior target information. Our contributions on class information exploitation are two-fold. First, we propose a supervised inversion model, Supervised Model Inversion (SMI). The proposed inversion model learns pixel-level features and data-to-class features from the rounded-outputs of the victim model and labeled auxiliary dataset. Second, we leverage victim model's rounded-outputs to guide the optimization of reconstructing inversion samples after trained inversion model. Our experimental results show that inversion samples reconstructed by SMI are more visually plausible with more details, comparing to the three representative model inversion attacks. We further perform an extensive study on various auxiliary dataset settings. It is found that the class combination in the auxiliary dataset rather than the number of classes that determines the quality of inversion samples. The ground-truth labels can improve the qualities of inversion samples but not essential to inversion attacks.

Published
2024
Full Text
View/download PDF

11. Clustering High-Dimensional Noisy Categorical Data.

Author

Tian, Zhiyi, Xu, Jiaming, and Tang, Jen

Abstract

AbstractClustering is a widely used unsupervised learning technique that groups data into homogeneous clusters. However, when dealing with real-world data that contain categorical values, existing algorithms can be computationally costly in high dimensions and can struggle with noisy data that has missing values. Furthermore, except for one algorithm, no others provide theoretical guarantees of clustering accuracy. In this article, we propose a general categorical data encoding method and a computationally efficient spectral-based algorithm to cluster high-dimensional noisy categorical data (nominal or ordinal). Under a statistical model for data on m attributes from n subjects in r clusters with missing probability ϵ, we show that our algorithm exactly recovers the true clusters with high probability when mn(1−ϵ)≥CMr2 log 3M, with M=max(n,m) and a fixed constant C. In addition, we show that mn(1−ϵ)2≥rδ/2 with 0<δ<1 is necessary for any algorithm to succeed with probability at least (1+δ)/2. In cases where m = n and r are fixed, the sufficient condition matches with the necessary condition up to a polylog(n) factor. In numerical studies our algorithm outperforms several existing algorithms in both clustering accuracy and computational efficiency. Supplementary materials for this article are available online. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

21. Clustering High-dimensional Noisy Categorical and Mixed Data

Author

Tian, Zhiyi

Subjects
Statistics, FOS: Mathematics
Abstract

Clustering is an unsupervised learning technique widely used to group data into homogeneous clusters. For many real-world data containing categorical values, existing algorithms are often computationally costly in high dimensions, do not work well on noisy data with missing values, and rarely provide theoretical guarantees on clustering accuracy. In this thesis, we propose a general categorical data encoding method and a computationally efficient spectral based algorithm to cluster high-dimensional noisy categorical (nominal or ordinal) data. Under a statistical model for data on m attributes from n subjects in r clusters with missing probability epsilon, we show that our algorithm exactly recovers the true clusters with high probability when mn(1-epsilon) >= CMr2 log3M, with M=max(n,m) and a fixed constant C. Moreover, we show that mn(1- epsilon)2 >= r *delta/2 with 0< delta

Published
2021
Full Text
View/download PDF

26. No-shows to primary care appointments: subsequent acute care utilization among diabetic patients

Author

Nuti Lynn A, Lawley Mark, Turkcan Ayten, Tian Zhiyi, Zhang Lingsong, Chang Karen, Willis Deanna R, and Sands Laura P

Subjects
No-show, Diabetes, Emergency department visits, Hospital admissions, Outcomes, Public aspects of medicine, RA1-1270
Abstract

Abstract Background Patients who no-show to primary care appointments interrupt clinicians’ efforts to provide continuity of care. Prior literature reveals no-shows among diabetic patients are common. The purpose of this study is to assess whether no-shows to primary care appointments are associated with increased risk of future emergency department (ED) visits or hospital admissions among diabetics. Methods A prospective cohort study was conducted using data from 8,787 adult diabetic patients attending outpatient clinics associated with a medical center in Indiana. The outcomes examined were hospital admissions or ED visits in the 6 months (182 days) following the patient’s last scheduled primary care appointment. The Andersen-Gill extension of the Cox proportional hazard model was used to assess risk separately for hospital admissions and ED visits. Adjustment was made for variables associated with no-show status and acute care utilization such as gender, age, race, insurance and co-morbid status. The interaction between utilization of the acute care service in the six months prior to the appointment and no-show was computed for each model. Results The six-month rate of hospital admissions following the last scheduled primary care appointment was 0.22 (s.d. = 0.83) for no-shows and 0.14 (s.d. = 0.63) for those who attended (p p Conclusions No-show to a primary care appointment is associated with increased risk for hospital admission among diabetics recently hospitalized.

Published
2012
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results