Duy Tung Khanh Nguyen

Mr. Duy Tung Khanh Nguyen


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
18 December 2023 in Future Internet
Verified
Journal Article
Open access
PDF file
DNDuy Tung Khanh Nguyen
Duy Tung Khanh Nguyen
DDDung Hoang Duong
Dung Hoang Duong
Willy SusiloWilly Susilo
Willy Susilo
Yang-Wai ChowYang-Wai Chow
Yang-Wai Chow
TTThe Anh Ta
The Anh Ta
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 ReLU, 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: ReLU, which facilitates the direct evaluation of the ReLU function on encrypted data, tackling the first limitation, and HeRefresh, which extends the feasible depth of neural network computations and mitigates the computational overhead, thereby addressing the second and third limitations. Based on HeReLU and HeRefresh protocols, we build a new framework for SNNI, named HeFUN. We prove that our protocols and the HeFUN framework are secure in the semi-honest security model. Empirical evaluations demonstrate that HeFUN 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, HeFUN achieves 99.16% accuracy with an inference latency of 1.501 s, surpassing the popular HE-based framework CryptoNets proposed by Gilad-Bachrach, which achieves 98.52% accuracy with an inference latency of 3.479 s.

13 October 2024
Verified
Book Chapter
Closed access
PDF file
DNDuy Tung Khanh Nguyen
Duy Tung Khanh Nguyen
DDDung Hoang Duong
Dung Hoang Duong
Willy SusiloWilly Susilo
Willy Susilo
Yang-Wai ChowYang-Wai Chow
Yang-Wai Chow

19 June 2025 in Pragmatic Cybersecurity
Verified
Journal Article
Open access
PDF file
DNDuy Tung Khanh Nguyen
Duy Tung Khanh Nguyen
DDDung Hoang Duong
Dung Hoang Duong
Yang-Wai ChowYang-Wai Chow
Yang-Wai Chow
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.