Trực Nguyễn - Academia.edu (original) (raw)

Papers by Trực Nguyễn

IEEE/ACM Transactions on Networking

Federated learning is known to be vulnerable to security and privacy issues. Existing research ha... more Federated learning is known to be vulnerable to security and privacy issues. Existing research has focused either on preventing poisoning attacks from users or on protecting user privacy of model updates. However, integrating these two lines of research remains a crucial challenge since they often conflict with one another with respect to the threat model. In this work, we develop a framework to combine secure aggregation with defense mechanisms against poisoning attacks from users, while maintaining their respective privacy guarantees. We leverage zero-knowledge proof protocol to let users run the defense mechanisms locally and attest the result to the central server without revealing any information about their model updates. Furthermore, we propose a new secure aggregation protocol for federated learning using homomorphic encryption that is robust against malicious users. Our framework enables the central server to identify poisoned model updates without violating the privacy guarantees of secure aggregation. Finally, we analyze the computation and communication complexity of our proposed solution and benchmark its performance.

IEEE Transactions on Computers

Since 2016, sharding has become an auspicious solution to tackle the scalability issue in legacy ... more Since 2016, sharding has become an auspicious solution to tackle the scalability issue in legacy blockchain systems. Despite its potential to strongly boost the blockchain throughput, sharding comes with its own security issues. To ease the process of deciding which shard to place transactions, existing sharding protocols use a hash-based transaction sharding in which the hash value of a transaction determines its output shard. Unfortunately, we show that this mechanism opens up a loophole that could be exploited to conduct a single-shard flooding attack, a type of Denial-of-Service (DoS) attack, to overwhelm a single shard that ends up reducing the performance of the system as a whole. To counter the single-shard flooding attack, we propose a countermeasure that essentially eliminates the loophole by rejecting the use of hash-based transaction sharding. The countermeasure leverages the Trusted Execution Environment (TEE) to let blockchain's validators securely execute a transaction sharding algorithm with a negligible overhead. We provide a formal specification for the countermeasure and analyze its security properties in the Universal Composability (UC) framework. Finally, a proof-of-concept is developed to demonstrate the feasibility and practicality of our solution.

The incredible growth of sensors and microcontroller units makes the task of real-time event moni... more The incredible growth of sensors and microcontroller units makes the task of real-time event monitoring in the Internet of Things (IoT) based applications easier and more practical. In order to effectively support the event management in IoT-based applications, we propose a framework that is based on the publish-subscribe model for detecting events from IoT sensor nodes and sending notifications to subscribers (end-users) via Internet, SMS, and Calling. With the exception of the advantages inherited from the publish-subscribe model, the further advantages of the proposed framework are the ease of use in terms of user configuration without any need of technical skills; the aid of security mechanisms to prevent network intrusion; and the minimum hardware resource requirement. Additionally, the proposed framework is applicable and adaptable to various platforms since it has been developed by using Boost C++ Libraries and CMake. To evaluate the proposed framework, we develop a prototype...

ArXiv, 2019

Due to high complexity of many modern machine learning models such as deep convolutional networks... more Due to high complexity of many modern machine learning models such as deep convolutional networks, understanding the cause of model's prediction is critical. Many explainers have been designed to give us more insights on the decision of complex classifiers. However, there is no common ground on evaluating the quality of different classification methods. Motivated by the needs for comprehensive evaluation, we introduce the c-Eval metric and the corresponding framework to quantify the explainer's quality on feature-based explainers of machine learning image classifiers. Given a prediction and the corresponding explanation on that prediction, c-Eval is the minimum-power perturbation that successfully alters the prediction while keeping the explanation's features unchanged. We also provide theoretical analysis linking the proposed parameter with the portion of predicted object covered by the explanation. Using a heuristic approach, we introduce the c-Eval plot, which not onl...

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2019

One of the major problems in current implementations of iterative double auction is that they rel... more One of the major problems in current implementations of iterative double auction is that they rely on a trusted third party to handle the auction process. This imposes the risk of single point of failures and monopoly. In this paper, we aim to tackle this problem by proposing a novel decentralized and trustless framework for iterative double auction based on blockchain. Our design adopts the smart contract and state channel technologies to enable a double auction process among parties that do not trust each other, while minimizing the blockchain transactions. We provide a formal development of the framework and highlight the security of our design against adversaries.

2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020

This paper presents a robust deep learning framework developed to detect respiratory diseases fro... more This paper presents a robust deep learning framework developed to detect respiratory diseases from recordings of respiratory sounds. The complete detection process firstly involves front end feature extraction where recordings are transformed into spectrograms that convey both spectral and temporal information. Then a back-end deep learning model classifies the features into classes of respiratory disease or anomaly. Experiments, conducted over the ICBHI benchmark dataset of respiratory sounds, evaluate the ability of the framework to classify sounds. Two main contributions are made in this paper. Firstly, we provide an extensive analysis of how factors such as respiratory cycle length, time resolution, and network architecture, affect final prediction accuracy. Secondly, a novel deep learning based framework is proposed for detection of respiratory diseases and shown to perform extremely well compared to state of the art methods. Clinical relevance-Respiratory disease, wheezes, crackles, Convolutional neural network (CNN), recurrent neural network (RNN).

Digital Signal Processing, 2021

This article proposes an encoder-decoder network model for Acoustic Scene Classification (ASC), t... more This article proposes an encoder-decoder network model for Acoustic Scene Classification (ASC), the task of identifying the scene of an audio recording from its acoustic signature. We make use of multiple low-level spectrogram features at the front-end, transformed into higher level features through a well-trained CNN-DNN front-end encoder. The high level features and their combination (via a trained feature combiner) are then fed into different decoder models comprising random forest regression, DNNs and a mixture of experts, for back-end classification. We report extensive experiments to evaluate the accuracy of this framework for various ASC datasets, including LITIS Rouen and IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) 2016 Task 1, 2017 Task 1, 2018 Tasks 1A & 1B and 2019 Tasks 1A & 1B. The experimental results highlight two main contributions; the first is an effective method for high-level feature extraction from multi-spectrogram input via the novel C-DNN architecture encoder network, and the second is the proposed decoder which enables the framework to achieve competitive results on various datasets. The fact that a single framework is highly competitive for several different challenges is an indicator of its robustness for performing general ASC tasks.

Computational Data and Social Networks, 2018

In this paper, we present how blockchain can be leveraged to tackle data privacy issues in Intern... more In this paper, we present how blockchain can be leveraged to tackle data privacy issues in Internet of Things (IoT). With the aid of smart contracts, we have developed a system model featuring a trustless access control management mechanism to ensure that users have full control over their data and can track how data are accessed by third-party services. Additionally, we propose a firmware update scheme using blockchain that helps prevent fraudulent data caused by IoT device tampering. Finally, we discuss how our proposed solution can strengthen the data privacy as well as tolerate common adversaries.

ACM Transactions on Internet Technology, 2021

Although the iterative double auction has been widely used in many different applications, one of... more Although the iterative double auction has been widely used in many different applications, one of the major problems in its current implementations is that they rely on a trusted third party to handle the auction process. This imposes the risk of single point of failures, monopoly, and bribery. In this article, we aim to tackle this problem by proposing a novel decentralized and trustless framework for iterative double auction based on blockchain. Our design adopts the smart contract and state channel technologies to enable a double auction process among parties that do not need to trust each other, while minimizing the blockchain transactions. In specific, we propose an extension to the original concept of state channels that can support multiparty computation. Then, we provide a formal development of the proposed framework and prove the security of our design against adversaries. Finally, we develop a proof-of-concept implementation of our framework using Elixir and Solidity, on w...

2016 8th International Workshop on Resilient Networks Design and Modeling (RNDM), 2016

This work presents a comprehensive performance comparison of our cross-layer resilient protocol s... more This work presents a comprehensive performance comparison of our cross-layer resilient protocol stack, ResTP-GeoDivRP against Multipath TCP (MPTCP). A profile-based challenge model is used to better represent different failure scenarios. Furthermore, our resilient protocol stack is implemented in the network simulator ns-3 and emulated in the KanREN testbed. The GeoDivRP routing protocol collects network statistics and calculates multiple geodiverse paths; these paths are provided upstack to our resilient transport protocol, ResTP, for resilient multipath communications. By providing multiple geodiverse paths, our ResTP-GeoDivRP protocol stack provides better path protection against regional failures than MPTCP.