Duy Tung Khanh Nguyen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Duy Tung Khanh Nguyen has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Dung Hoang Duong
University of Wollongong
3 shared publications - Yang-Wai Chow
University of Wollongong
3 shared publications - Willy Susilo
Institute of Cybersecurity and Cryptology, School of Computing and Information Technology, University of Wollongong, Wollongong, NSW 2522, Australia
2 shared publications - The-Anh Ta
CSIRO’s Data61
1 shared publication
Latest Publications
- Open Access
- 19 June 2025
- Published by Scilight Press Pty Ltd in Pragmatic Cybersecurity
- Vol. 1 (1) , 2
BadEmbNets: A Framework for Backdoor Attacks against Visually-Aware Recommender System
Recommender systems play a pivotal role in e-commerce, social media, and content streaming platforms by personalizing user experiences and driving engagement. While enhancing the performance of these systems is crucial, ensuring their robustness is equally important to safeguard against security threats. Despite extensive research addressing adversarial and shilling attacks on recommender systems, backdoor attacks remain underexplored. This paper introduces BadEmbNets, an innovative framework for executing backdoor attacks on visually-aware recommender systems. Our experiments demonstrate that an attacker can effectively elevate the rank of compromised items by embedding triggers in their images without affecting the performance of benign items. This work motivates further research into backdoor attacks against recommender systems.
- 19 June 2025
- Published by Scilight Press Pty Ltd in Pragmatic Cybersecurity
- Vol. 1 (1) , 2
Open AccessBadEmbNets: A Framework for Backdoor Attacks against Visually-Aware Recommender System
Recommender systems play a pivotal role in e-commerce, social media, and content streaming platforms by personalizing user experiences and driving engagement. While enhancing the performance of these systems is crucial, ensuring their robustness is equally important to safeguard against security threats. Despite extensive research addressing adversarial and shilling attacks on recommender systems, backdoor attacks remain underexplored. This paper introduces BadEmbNets, an innovative framework for executing backdoor attacks on visually-aware recommender systems. Our experiments demonstrate that an attacker can effectively elevate the rank of compromised items by embedding triggers in their images without affecting the performance of benign items. This work motivates further research into backdoor attacks against recommender systems.
- 13 October 2024
- Published by Springer Nature
- p. 413-438
HeSUN: Homomorphic Encryption for Secure Unbounded Neural Network Inference
- 13 October 2024
- Published by Springer Nature
- p. 413-438
HeSUN: Homomorphic Encryption for Secure Unbounded Neural Network Inference
- Open Access
- 18 December 2023
- Published by MDPI AG in Future Internet
- Vol. 15 (12) , 407
HeFUN: Homomorphic Encryption for Unconstrained Secure Neural Network Inference
Homomorphic encryption (HE) has emerged as a pivotal technology for secure neural network inference (SNNI), offering privacy-preserving computations on encrypted data. Despite active developments in this field, HE-based SNNI frameworks are impeded by three inherent limitations. Firstly, they cannot evaluate non-linear functions such as , the most widely adopted activation function in neural networks. Secondly, the permitted number of homomorphic operations on ciphertexts is bounded, consequently limiting the depth of neural networks that can be evaluated. Thirdly, the computational overhead associated with HE is prohibitively high, particularly for deep neural networks. In this paper, we introduce a novel paradigm designed to address the three limitations of HE-based SNNI. Our approach is an interactive approach that is solely based on HE, called iLHE. Utilizing the idea of iLHE, we present two protocols: , which facilitates the direct evaluation of the function on encrypted data, tackling the first limitation, and , which extends the feasible depth of neural network computations and mitigates the computational overhead, thereby addressing the second and third limitations. Based on and protocols, we build a new framework for SNNI, named . We prove that our protocols and the framework are secure in the semi-honest security model. Empirical evaluations demonstrate that surpasses current HE-based SNNI frameworks in multiple aspects, including security, accuracy, the number of communication rounds, and inference latency. Specifically, for a convolutional neural network with four layers on the MNIST dataset, achieves accuracy with an inference latency of s, surpassing the popular HE-based framework CryptoNets proposed by Gilad-Bachrach, which achieves accuracy with an inference latency of s.- 18 December 2023
- Published by MDPI AG in Future Internet
- Vol. 15 (12) , 407
Open AccessHeFUN: Homomorphic Encryption for Unconstrained Secure Neural Network Inference
Homomorphic encryption (HE) has emerged as a pivotal technology for secure neural network inference (SNNI), offering privacy-preserving computations on encrypted data. Despite active developments in this field, HE-based SNNI frameworks are impeded by three inherent limitations. Firstly, they cannot evaluate non-linear functions such as , the most widely adopted activation function in neural networks. Secondly, the permitted number of homomorphic operations on ciphertexts is bounded, consequently limiting the depth of neural networks that can be evaluated. Thirdly, the computational overhead associated with HE is prohibitively high, particularly for deep neural networks. In this paper, we introduce a novel paradigm designed to address the three limitations of HE-based SNNI. Our approach is an interactive approach that is solely based on HE, called iLHE. Utilizing the idea of iLHE, we present two protocols: , which facilitates the direct evaluation of the function on encrypted data, tackling the first limitation, and , which extends the feasible depth of neural network computations and mitigates the computational overhead, thereby addressing the second and third limitations. Based on and protocols, we build a new framework for SNNI, named . We prove that our protocols and the framework are secure in the semi-honest security model. Empirical evaluations demonstrate that surpasses current HE-based SNNI frameworks in multiple aspects, including security, accuracy, the number of communication rounds, and inference latency. Specifically, for a convolutional neural network with four layers on the MNIST dataset, achieves accuracy with an inference latency of s, surpassing the popular HE-based framework CryptoNets proposed by Gilad-Bachrach, which achieves accuracy with an inference latency of s.