Thang Hoang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Thang Hoang has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Attila Altay Yavuz
University of South Florida, Tampa, USA
4 shared publications Jorge Guajardo
Robert Bosch LLC, Research and Technology Center, Pittsburgh, PA
3 shared publications- Arman Riasi
Virginia Tech, Blacksburg, VA, USA
2 shared publications Attila A. Yavuz
The Department of Computer Science and Engineering, University of South Florida, Tampa, Florida
2 shared publications- Haodi Wang
City University of Hong Kong
2 shared publications - Atharva Haldankar
Virginia Tech, United States of America
1 shared publication
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1910-1924
Efficient Single-Round Obfuscation of Search and Result Patterns in Searchable Encryption
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1910-1924
Open AccessEfficient Single-Round Obfuscation of Search and Result Patterns in Searchable Encryption
- Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1053-1067
Zero-Knowledge AI Inference with High Precision
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1053-1067
Open AccessZero-Knowledge AI Inference with High Precision
- Open Access
- 30 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 465-479
Breaking Privacy in Model-Heterogeneous Federated Learning
Federated learning (FL) allows multiple distrustful clients to collaboratively train a machine learning model. In FL, data never leaves client devices; instead, clients only share locally computed gradients with a central server. As individual gradients may leak information about a given client’s dataset, secure aggregation was proposed. With secure aggregation, the server only receives the aggregate gradient update from the set of all sampled clients without being able to access any individual gradient. One challenge in FL is the systems-level heterogeneity that is quite often present among client devices. Specifically, clients in the FL protocol may have varying levels of compute power, on-device memory, and communication bandwidth. These limitations are addressed by model-heterogeneous FL schemes, where clients are able to train on subsets of the global model. Despite the benefits of model-heterogeneous schemes in addressing systems-level challenges, the implications of these schemes on client privacy have not been thoroughly investigated. In this paper, we investigate whether the nature of model distribution and the computational heterogeneity among client devices in model-heterogeneous FL schemes may result in the server being able to recover sensitive data from target clients. To this end, we propose two attacks in the model-heterogeneous FL setting, even with secure aggregation in place. We call these attacks the Convergence Rate Attack and the Rolling Model Attack. The Convergence Rate Attack targets schemes where clients train on the same subset of the global model, while the Rolling Model Attack targets schemes where model parameters are dynamically updated each round. We show that a malicious adversary can compromise the model and data confidentiality of a target group of clients. We evaluate our attacks on the MNIST and CIFAR-10 datasets and show that using our techniques, an adversary can reconstruct data samples with near perfect accuracy for batch sizes of up to 20 samples.
- 30 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 465-479
Open AccessBreaking Privacy in Model-Heterogeneous Federated Learning
Federated learning (FL) allows multiple distrustful clients to collaboratively train a machine learning model. In FL, data never leaves client devices; instead, clients only share locally computed gradients with a central server. As individual gradients may leak information about a given client’s dataset, secure aggregation was proposed. With secure aggregation, the server only receives the aggregate gradient update from the set of all sampled clients without being able to access any individual gradient. One challenge in FL is the systems-level heterogeneity that is quite often present among client devices. Specifically, clients in the FL protocol may have varying levels of compute power, on-device memory, and communication bandwidth. These limitations are addressed by model-heterogeneous FL schemes, where clients are able to train on subsets of the global model. Despite the benefits of model-heterogeneous schemes in addressing systems-level challenges, the implications of these schemes on client privacy have not been thoroughly investigated. In this paper, we investigate whether the nature of model distribution and the computational heterogeneity among client devices in model-heterogeneous FL schemes may result in the server being able to recover sensitive data from target clients. To this end, we propose two attacks in the model-heterogeneous FL setting, even with secure aggregation in place. We call these attacks the Convergence Rate Attack and the Rolling Model Attack. The Convergence Rate Attack targets schemes where clients train on the same subset of the global model, while the Rolling Model Attack targets schemes where model parameters are dynamically updated each round. We show that a malicious adversary can compromise the model and data confidentiality of a target group of clients. We evaluate our attacks on the MNIST and CIFAR-10 datasets and show that using our techniques, an adversary can reconstruct data samples with near perfect accuracy for batch sizes of up to 20 samples.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (2) , 1347-1364
An Efficient and Zero-Knowledge Classical Machine Learning Inference Pipeline
Machine Learning as a Service (MLaaS) offers powerful data analytics services to clients with limited resources. However, it still raises concerns about the integrity of delegated computation and the privacy of the server's model parameters. To address these issues, zero-knowledge Machine Learning (zkML) has been suggested for computation verifiability with privacy guarantee for ML models. Nevertheless, the existing zkML schemes focus on only one classical ML classification algorithm or deep neural networks, which may not achieve satisfactory accuracy or require large-scale training data and model parameters, thus limiting their usefulness in certain applications. In this paper, we propose ezDPS, an efficient and zero-knowledge scheme for classical ML inference that processes data in multiple stages for improved accuracy. Unlike prior works, each stage of the ezDPS pipeline is based on a well-established classical ML algorithm, including Discrete Wavelet Transformation, Zero-Score Normalization, Principal Components Analysis, and Support Vector Machine. We design new gadgets to prove various ML operations effectively. Our implementation of ezDPS has been fully tested on real datasets, and experimental results show that it is up to three orders of magnitude more efficient than generic circuit-based approaches, while also maintaining greater accuracy than single ML classification approaches.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (2) , 1347-1364
An Efficient and Zero-Knowledge Classical Machine Learning Inference Pipeline
Machine Learning as a Service (MLaaS) offers powerful data analytics services to clients with limited resources. However, it still raises concerns about the integrity of delegated computation and the privacy of the server's model parameters. To address these issues, zero-knowledge Machine Learning (zkML) has been suggested for computation verifiability with privacy guarantee for ML models. Nevertheless, the existing zkML schemes focus on only one classical ML classification algorithm or deep neural networks, which may not achieve satisfactory accuracy or require large-scale training data and model parameters, thus limiting their usefulness in certain applications. In this paper, we propose ezDPS, an efficient and zero-knowledge scheme for classical ML inference that processes data in multiple stages for improved accuracy. Unlike prior works, each stage of the ezDPS pipeline is based on a well-established classical ML algorithm, including Discrete Wavelet Transformation, Zero-Score Normalization, Principal Components Analysis, and Support Vector Machine. We design new gadgets to prove various ML operations effectively. Our implementation of ezDPS has been fully tested on real datasets, and experimental results show that it is up to three orders of magnitude more efficient than generic circuit-based approaches, while also maintaining greater accuracy than single ML classification approaches.
- Open Access
- 19 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 115-126
Exploiting Update Leakage in Searchable Symmetric Encryption
Dynamic Searchable Symmetric Encryption (DSSE) provides efficient techniques for securely searching and updating an encrypted database. However, efficient DSSE schemes leak some sensitive information to the server. Recent works have implemented forward and backward privacy as security properties to reduce the amount of information leaked during update operations. Many attacks have shown that leakage from search operations can be abused to compromise the privacy of client queries. However, the attack literature has not rigorously investigated techniques to abuse update leakage. In this work, we investigate update leakage under DSSE schemes with forward and backward privacy from the perspective of a passive adversary. We propose two attacks based on a maximum likelihood estimation approach, the UFID Attack and the UF Attack, which target forward-private DSSE schemes with no backward privacy and Level 2 backward privacy, respectively. These are the first attacks to show that it is possible to leverage the frequency and contents of updates to recover client queries. We propose a variant of each attack which allows the update leakage to be combined with search pattern leakage to achieve higher accuracy. We evaluate our attacks against a real-world dataset and show that using update leakage can improve the accuracy of attacks against DSSE schemes, especially those without backward privacy.
- 19 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 115-126
Open AccessExploiting Update Leakage in Searchable Symmetric Encryption
Dynamic Searchable Symmetric Encryption (DSSE) provides efficient techniques for securely searching and updating an encrypted database. However, efficient DSSE schemes leak some sensitive information to the server. Recent works have implemented forward and backward privacy as security properties to reduce the amount of information leaked during update operations. Many attacks have shown that leakage from search operations can be abused to compromise the privacy of client queries. However, the attack literature has not rigorously investigated techniques to abuse update leakage. In this work, we investigate update leakage under DSSE schemes with forward and backward privacy from the perspective of a passive adversary. We propose two attacks based on a maximum likelihood estimation approach, the UFID Attack and the UF Attack, which target forward-private DSSE schemes with no backward privacy and Level 2 backward privacy, respectively. These are the first attacks to show that it is possible to leverage the frequency and contents of updates to recover client queries. We propose a variant of each attack which allows the update leakage to be combined with search pattern leakage to achieve higher accuracy. We evaluate our attacks against a real-world dataset and show that using update leakage can improve the accuracy of attacks against DSSE schemes, especially those without backward privacy.
- Open Access
- 5 February 2020
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Privacy and Security
- Vol. 23 (1) , 1-35
A Multi-server ORAM Framework with Constant Client Bandwidth Blowup
Oblivious Random Access Machine (ORAM) allows a client to hide the access pattern when accessing sensitive data on a remote server. It is known that there exists a logarithmic communication lower bound on any passive ORAM construction, where the server only acts as the storage service. This overhead, however, was shown costly for some applications. Several active ORAM schemes with server computation have been proposed to overcome this limitation. However, they mostly rely on costly homomorphic encryptions, whose performance is worse than passive ORAM. In this article, we propose S 3 ORAM, a new multi-server ORAM framework, which features O (1) client bandwidth blowup and low client storage without relying on costly cryptographic primitives. Our key idea is to harness Shamir Secret Sharing and a multi-party multiplication protocol on applicable binary tree-ORAM paradigms. This strategy allows the client to instruct the server(s) to perform secure and efficient computation on his/her behalf with a low intervention thereby, achieving a constant client bandwidth blowup and low server computational overhead. Our framework can also work atop a general k -ary tree ORAM structure ( k ≥ 2). We fully implemented our framework, and strictly evaluated its performance on a commodity cloud platform (Amazon EC2). Our comprehensive experiments confirmed the efficiency of S 3 ORAM framework, where it is approximately 10× faster than the most efficient passive ORAM (i.e., Path-ORAM) for a moderate network bandwidth while being three orders of magnitude faster than active ORAM with O (1) bandwidth blowup (i.e., Onion-ORAM). We have open-sourced the implementation of our framework for public testing and adaptation.
- 5 February 2020
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Privacy and Security
- Vol. 23 (1) , 1-35
Open AccessA Multi-server ORAM Framework with Constant Client Bandwidth Blowup
Oblivious Random Access Machine (ORAM) allows a client to hide the access pattern when accessing sensitive data on a remote server. It is known that there exists a logarithmic communication lower bound on any passive ORAM construction, where the server only acts as the storage service. This overhead, however, was shown costly for some applications. Several active ORAM schemes with server computation have been proposed to overcome this limitation. However, they mostly rely on costly homomorphic encryptions, whose performance is worse than passive ORAM. In this article, we propose S 3 ORAM, a new multi-server ORAM framework, which features O (1) client bandwidth blowup and low client storage without relying on costly cryptographic primitives. Our key idea is to harness Shamir Secret Sharing and a multi-party multiplication protocol on applicable binary tree-ORAM paradigms. This strategy allows the client to instruct the server(s) to perform secure and efficient computation on his/her behalf with a low intervention thereby, achieving a constant client bandwidth blowup and low server computational overhead. Our framework can also work atop a general k -ary tree ORAM structure ( k ≥ 2). We fully implemented our framework, and strictly evaluated its performance on a commodity cloud platform (Amazon EC2). Our comprehensive experiments confirmed the efficiency of S 3 ORAM framework, where it is approximately 10× faster than the most efficient passive ORAM (i.e., Path-ORAM) for a moderate network bandwidth while being three orders of magnitude faster than active ORAM with O (1) bandwidth blowup (i.e., Onion-ORAM). We have open-sourced the implementation of our framework for public testing and adaptation.
- 30 September 2019
- Published by SAGE Publications in Journal of Computer Security
- Vol. 27 (6) , 649-676
A multi-server oblivious dynamic searchable encryption framework
Data privacy is one of the main concerns for data outsourcing on the cloud. Although standard encryption can provide confidentiality, it prevents the client from searching/retrieving meaningful information on the outsourced data thereby, degrading th
- 30 September 2019
- Published by SAGE Publications in Journal of Computer Security
- Vol. 27 (6) , 649-676
A multi-server oblivious dynamic searchable encryption framework
Data privacy is one of the main concerns for data outsourcing on the cloud. Although standard encryption can provide confidentiality, it prevents the client from searching/retrieving meaningful information on the outsourced data thereby, degrading th
- 1 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 14 (6) , 1675-1689
A Secure Searchable Encryption Framework for Privacy-Critical Cloud Storage Services
- 1 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 14 (6) , 1675-1689
A Secure Searchable Encryption Framework for Privacy-Critical Cloud Storage Services
- Open Access
- 24 December 2018
- Published by Privacy Enhancing Technologies Symposium Advisory Board in Proceedings on Privacy Enhancing Technologies
- Vol. 2019 (1) , 172-191
Hardware-Supported ORAM in Effect: Practical Oblivious Search and Update on Very Large Dataset
The ability to query and update over encrypted data is an essential feature to enable breach-resilient cyber-infrastructures. Statistical attacks on searchable encryption (SE) have demonstrated the importance of sealing information leaks in access patterns. In response to such attacks, the community has proposed the Oblivious Random Access Machine (ORAM). However, due to the logarithmic communication overhead of ORAM, the composition of ORAM and SE is known to be costly in the conventional client-server model, which poses a critical barrier toward its practical adaptations. In this paper, we propose a novel hardware-supported privacy-enhancing platform called Practical Oblivious Search and Update Platform (POSUP), which enables oblivious keyword search and update operations on large datasets with high efficiency. We harness Intel SGX to realize efficient oblivious data structures for oblivious search/update purposes. We implemented POSUP and evaluated its performance on a Wikipedia dataset containing ≥229 keyword-file pairs. Our implementation is highly efficient, taking only 1 ms to access a 3 KB block with Circuit-ORAM. Our experiments have shown that POSUP offers up to 70× less end-to-end delay with 100× reduced network bandwidth consumption compared with the traditional ORAM-SE composition without secure hardware. POSUP is also at least 4.5× faster for up to 99.5% of keywords that can be searched compared with state-of-the-art Intel SGX-assisted search platforms.
- 24 December 2018
- Published by Privacy Enhancing Technologies Symposium Advisory Board in Proceedings on Privacy Enhancing Technologies
- Vol. 2019 (1) , 172-191
Open AccessHardware-Supported ORAM in Effect: Practical Oblivious Search and Update on Very Large Dataset
The ability to query and update over encrypted data is an essential feature to enable breach-resilient cyber-infrastructures. Statistical attacks on searchable encryption (SE) have demonstrated the importance of sealing information leaks in access patterns. In response to such attacks, the community has proposed the Oblivious Random Access Machine (ORAM). However, due to the logarithmic communication overhead of ORAM, the composition of ORAM and SE is known to be costly in the conventional client-server model, which poses a critical barrier toward its practical adaptations. In this paper, we propose a novel hardware-supported privacy-enhancing platform called Practical Oblivious Search and Update Platform (POSUP), which enables oblivious keyword search and update operations on large datasets with high efficiency. We harness Intel SGX to realize efficient oblivious data structures for oblivious search/update purposes. We implemented POSUP and evaluated its performance on a Wikipedia dataset containing ≥229 keyword-file pairs. Our implementation is highly efficient, taking only 1 ms to access a 3 KB block with Circuit-ORAM. Our experiments have shown that POSUP offers up to 70× less end-to-end delay with 100× reduced network bandwidth consumption compared with the traditional ORAM-SE composition without secure hardware. POSUP is also at least 4.5× faster for up to 99.5% of keywords that can be searched compared with state-of-the-art Intel SGX-assisted search platforms.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cloud Computing
- Vol. 9 (2) , 598-609
Efficient Oblivious Data Structures for Database Services on the Cloud
Database-as-a-service (DBaaS) allows the client to store and manage structured data on the cloud remotely. Despite its merits, DBaaS also brings significant privacy issues. Existing encryption techniques (e.g., SQL-aware encryption) can mitigate privacy concerns, but they still leak information through access patterns which are vulnerable to statistical inference attacks. Oblivious Random Access Machine (ORAM) can seal such leakages, but the recent studies showed significant challenges on the integration of ORAM into databases. Specifically, the direct usage of ORAM on databases is not only costly but also permits very limited query functionalities. We propose new oblivious data structures called Oblivious Matrix Structure (OMAT) and Oblivious Tree Structure (OTREE), which allow tree-based ORAM to be integrated into database systems in a more efficient manner with diverse query functionalities supported. OMAT provides special ORAM packaging strategies for table structures, which not only offers a significantly better performance but also enables a broad range of query types that may not be practical in existing frameworks. OTREE allows oblivious conditional queries to be deployed on tree-indexed databases more efficient than existing techniques. We fully implemented our proposed techniques and evaluated their performance on a real cloud database with various metrics, compared with state-of-the-art counterparts.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cloud Computing
- Vol. 9 (2) , 598-609
Efficient Oblivious Data Structures for Database Services on the Cloud
Database-as-a-service (DBaaS) allows the client to store and manage structured data on the cloud remotely. Despite its merits, DBaaS also brings significant privacy issues. Existing encryption techniques (e.g., SQL-aware encryption) can mitigate privacy concerns, but they still leak information through access patterns which are vulnerable to statistical inference attacks. Oblivious Random Access Machine (ORAM) can seal such leakages, but the recent studies showed significant challenges on the integration of ORAM into databases. Specifically, the direct usage of ORAM on databases is not only costly but also permits very limited query functionalities. We propose new oblivious data structures called Oblivious Matrix Structure (OMAT) and Oblivious Tree Structure (OTREE), which allow tree-based ORAM to be integrated into database systems in a more efficient manner with diverse query functionalities supported. OMAT provides special ORAM packaging strategies for table structures, which not only offers a significantly better performance but also enables a broad range of query types that may not be practical in existing frameworks. OTREE allows oblivious conditional queries to be deployed on tree-indexed databases more efficient than existing techniques. We fully implemented our proposed techniques and evaluated their performance on a real cloud database with various metrics, compared with state-of-the-art counterparts.