Zesheng Chen

Dr. Zesheng Chen

orcid

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
21 December 2024 in Electronics
Verified
Journal Article
Open access
PDF file
SSSanidhya Sharma
Sanidhya Sharma
ZCZesheng Chen
Zesheng Chen
Network Intrusion Detection Systems (NIDSs) are vital for safeguarding Internet of Things (IoT) networks from malicious attacks. Modern NIDSs utilize Machine Learning (ML) techniques to combat evolving threats. This study systematically examined adversarial attacks originating from the image domain against ML-based NIDSs, while incorporating a diverse selection of ML models. Specifically, we evaluated both white-box and black-box attacks on nine commonly used ML-based NIDS models. We analyzed the Projected Gradient Descent (PGD) attack, which uses gradient descent on input features, transfer attacks, the score-based Zeroth-Order Optimization (ZOO) attack, and two decision-based attacks: Boundary and HopSkipJump. Using the NSL-KDD dataset, we assessed the accuracy of the ML models under attack and the success rate of the adversarial attacks. Our findings revealed that the black-box decision-based attacks were highly effective against most of the ML models, achieving an attack success rate exceeding 86% across eight models. Additionally, while the Logistic Regression and Multilayer Perceptron models were highly susceptible to all the attacks studied, the instance-based ML models, such as KNN and Label Spreading, exhibited resistance to these attacks. These insights will contribute to the development of more robust NIDSs against adversarial attacks in IoT environments.

9 September 2019 in IEEE Access
Verified
Journal Article
Open access
ZCZesheng Chen
Zesheng Chen
Epidemic models have been a widely used mathematical tool in network security and social networks to study malware propagation and information dissemination. However, the relationships and the differences of discrete-time and continuous-time epidemic models in networks have not been systematically studied yet. In this paper, we focus on the susceptible-infectious model and attempt to connect and compare different discrete-time and continuous-time epidemic models through both theoretical analysis and empirical verification. We find that epidemic models can be distinguished based on whether a model considers the following three key factors: time intervals, spatial dependence among nodes, and linearization. We theoretically and empirically show that ignoring time intervals, assuming spatial independence among nodes, or applying linearization can cause a model to possibly over-predict the propagation speed of an epidemic. Especially, we discover that a widely used continuous-time epidemic model cannot accurately characterize the spread of the actual epidemic by ignoring both time intervals and spatial dependence among nodes.

17 August 2022 in Algorithms
Verified
Journal Article
Open access
PDF file
ZCZesheng Chen
Zesheng Chen
LCLi-Chi Chang
Li-Chi Chang
CCChao Chen
Chao Chen
GWGuoping Wang
Guoping Wang
Zhuming BiZhuming Bi
Zhuming Bi
Speaker verification systems use human voices as an important biometric to identify legitimate users, thus adding a security layer to voice-controlled Internet-of-things smart homes against illegal access. Recent studies have demonstrated that speaker verification systems are vulnerable to adversarial attacks such as FakeBob. The goal of this work is to design and implement a simple and light-weight defense system that is effective against FakeBob. We specifically study two opposite pre-processing operations on input audios in speak verification systems: denoising that attempts to remove or reduce perturbations and noise-adding that adds small noise to an input audio. Through experiments, we demonstrate that both methods are able to weaken the ability of FakeBob attacks significantly, with noise-adding achieving even better performance than denoising. Specifically, with denoising, the targeted attack success rate of FakeBob attacks can be reduced from 100% to 56.05% in GMM speaker verification systems, and from 95% to only 38.63% in i-vector speaker verification systems, respectively. With noise adding, those numbers can be further lowered down to 5.20% and 0.50%, respectively. As a proactive measure, we study several possible adaptive FakeBob attacks against the noise-adding method. Experiment results demonstrate that noise-adding can still provide a considerable level of protection against these countermeasures.

17 April 2023 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
ZCZesheng Chen
Zesheng Chen
Speaker verification (SV) systems have been widely used in smartphones and Internet of Things devices to identify legitimate users. In recent work, it has been shown that adversarial attacks, such as FAKEBOB, can work effectively against SV systems. The goal of this article is to design a detector that can distinguish an original audio from an audio contaminated by adversarial attacks, if the original audio and the audio before contaminated by the attack have a similar signal-to-noise ratio. Specifically, our designed detector, called MEH-FEST, calculates the minimum energy in an audio signal’s high-frequency band through the short-time Fourier transform and uses it as a detection metric. Through both analysis and experiments, we show that our proposed detector is easy to implement, fast to process an input audio, and effective in determining whether an audio is corrupted by FAKEBOB attacks. The experimental results indicate that the detector is extremely effective: with near zero false-positive and false-negative rates for detecting FAKEBOB attacks in Gaussian mixture model (GMM) and i-vector SV systems. Moreover, adaptive adversarial attacks against our proposed detector and their countermeasures are discussed and studied, showing the game between attackers and defenders.

1 January 2010 in International Journal of Security and Networks
Verified
Journal Article
Closed access
ZCZesheng Chen
Zesheng Chen
CCChao Chen
Chao Chen
Qian WangQian Wang
Qian Wang
In this work, we present a novel intelligent botnet, called the delay-tolerant botnet, that intentionally adds random delays to command propagation and endeavours to avoid detection. We then study the scalability of delay-tolerant botnets. Specifically, we apply mathematical analysis to derive the average delay required to distribute a command to all bots in three types of command and control architectures: centralised, distributed, and hybrid delay-tolerant botnets. We find that in all cases, the delay increases approximately logarithmically with the number of bots, indicating that the delay-tolerant botnets are scalable. Finally, we verify the analytical results by simulations.

17 July 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
ZCZesheng Chen
Zesheng Chen
Jack LiJack Li
Jack Li
CCChao Chen
Chao Chen
Speaker verification (SV) systems, crucial for securing online banking and Internet of Things devices, employ human voice biometrics to identify users. However, as these state-of-the-art systems rely on machine learning models, they are susceptible to adversarial attacks. Presently, there exists no defense system entirely immune to every form of adversarial attack. This work aims to develop a defense mechanism capable of effectively countering a broad spectrum of known adversarial threats. Our approach introduces an ensemble defense system that integrates the minimum energy in high frequencies for short time (MEH-FEST) and noise-adding (NA) strategies. To evaluate the performance of a defense system, a revised measure, namely the Refined F1 score, which incorporates the maximum false negative rate (MFNR) instead of the false negative rate in the traditional F1 score, is proposed. Experimental results reveal that our defense system achieves an MFNR 13.5% across 110 adversarial attacks. Consequently, while an SV system with a singular defense strategy may reach a maximum refined F1 score of 0.16, our ensemble defense system significantly improves performance, achieving a score of 0.91. This underscores its enhanced effectiveness in protecting against adversarial attacks. Furthermore, an ensemble attack method is designed to counter the proposed defense, incorporating two adaptive attacks against the NA defense and a novel strategy against the MEH-FEST detection. Experiments demonstrate that this ensemble attack significantly diminishes the effectiveness of the ensemble defenses.