Xiaoying Qiu

Xiaoying Qiu


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
3 February 2020 in IEEE Access
Verified
Journal Article
Open access
XQXiaoying Qiu
Xiaoying Qiu
JDJianmei Dai
Jianmei Dai
MHMonson Hayes
Monson Hayes
In communications, innovative paradigm shifts have emerged in integrating various devices into the network to provide advanced and intelligent services. However, various security threats may occur that may not always be detected using traditional cryptographic techniques. Secure authentication is of paramount importance in modern wireless systems. This paper focusses on robust authentication in a time-varying communication environment where conventional authentication mechanisms are severely limited. We propose an Adaptive Neural Network (ANN) as an intelligent authentication process to improve detection accuracy. Specifically, a Data-Adaptive Matrix (DAM) is designed to track time-varying channel features. By utilizing a convolutional neural network as an intelligent authenticator, the proposed approach integrates deep feature extraction and attack detection, hence, leading to effective physical layer security. To evaluate the system, the ANN is prototyped on a universal software radio peripheral (USRP) and its authentication performance is evaluated in a conference room environment. Experimental results show that the ANN is effective in tackling the challenges of physical layer authentication under interference conditions, and is effective in time-varying environments.

20 September 2018 in IEEE Access
Verified
Journal Article
Open access
XQXiaoying Qiu
Xiaoying Qiu
TJTing Jiang
Ting Jiang
SWSheng Wu
Sheng Wu
MHMonson Hayes
Monson Hayes
Wireless networks strive to integrate information technology into every corner of the world. This openness of radio propagation is one reason why holistic wireless security mechanisms only rarely enter the picture. In this paper, we propose a physical (PHY)-layer security authentication scheme that takes advantage of channel randomness to detect spoofing attacks in wireless networks. Unlike most existing authentication techniques that rely on comparing message information between the legitimate user and potential spoofer, our proposed authentication scheme uses a Gaussian mixture model (GMM) to detect spoofing attackers. Probabilistic models of different transmitters are used to cluster messages. Furthermore, a 2-D feature measure space is exploited to preprocess the channel information. Training data for a spoofer operating through an unknown channel, a pseudo adversary model is developed to enhance the spoofing detection performance. Monte Carlo simulations are used to evaluate the detection performance of the GMM-based PHY-layer authentication scheme. The results show that the probability of detecting a spoofer is higher than that obtained using similar approaches.

28 November 2019 in IEEE Access
Verified
Journal Article
Open access
XQXiaoying Qiu
Xiaoying Qiu
ZDZhiguo Du
Zhiguo Du
XSXuan Sun
Xuan Sun
Security provisioning has become a key issue in wireless multimedia networks due to their vital roles in supporting various services. Conventional security solutions have deficiencies in computing efficiency and addressing emerging security challenges. In addition, traditional upper-layer authentication ignores the protection of the physical layer, leading to severe privacy data leakage. In this paper, we envision a new deep learning (DL)-enabled security authentication scheme to overcome these issues, while implementing Blind Feature Learning (BFL) and Lightweight Physical Layer Authentication (LPLA). Specifically, an intelligent authentication method is developed by exploring neural networks at the data collection unit to learn the characteristics of data. Then we propose a holistic authentication scheme based on machine learning to identify malicious multimedia devices. Experimental analysis verifies that the proposed scheme can guarantee the privacy of wireless multimedia sensors and achieve lightweight authentication. Performance results indicate that artificial intelligence-enabled authentication scheme improves the overall security of multimedia networks.

1 February 2020 in Medicine
Verified
Journal Article
Open access
XQXiaoying Qiu
Xiaoying Qiu
QZQiyu Zhao
Qiyu Zhao
ZYZhengdu Ye
Zhengdu Ye
LMLang Meng
Lang Meng
CYChunhong Yan
Chunhong Yan
TJTian’an Jiang
Tian’an Jiang
To analyze the degree and pattern of influence of contrast-enhanced ultrasonography (CEUS) on the Bosniak classification system for complex renal cystic mass as compared with conventional ultrasonography (US). One hundred two consecutive patients with complex renal cystic masses were retrospectively analyzed. The diagnostic performance of the Conventional US and CEUS were evaluated separately for malignant and benign lesions. The diagnostic concordance rates were calculated according to pathologic diagnoses. ROC curve analysis determined the confidence in the diagnostic accuracy by calculating the area under each ROC curve. Compared to the Conventional US, septae number, wall and/or septae thickness, solid component and the Bosniak classification changed in 17 (16.7%), 39 (38.2%), 31 (30.4%), and 67 (65.7%) patients as compared with 0 (0.0%), 21 (20.6%), 31 (30.4%), and 37 (36.3%) of the treatment strategy that changed after CEUS respectively. The diagnostic performance of CEUS showed overall higher in terms of sensitivity (100.0 vs 97.2%); specificity (90.9 vs 62.1%); positive predictive value (PPV) (85.7 vs 58.3%); negative predictive value (NPV) (100.0 vs 97.6%); and the concordance with pathology (kappa = 0.876 vs 0.515). CEUS had a higher diagnostic confidence (P < .05) according to the area under the ROC curve (AUC = 0.968 vs 0.799).CEUS performed better than the Conventional US in the diagnosis of complex renal cystic mass, and it might be considered as the first tool to evaluate a complex cystic renal mass, especially for these Bosniak III masses displaying the presence of hemorrhage or infection.

9 August 2021 in Sensors
Verified
Journal Article
Open access
PDF file
XQXiaoying Qiu
Xiaoying Qiu
XSXuan Sun
Xuan Sun
MHMonson Hayes
Monson Hayes
The performance of classical security authentication models can be severely affected by imperfect channel estimation as well as time-varying communication links. The commonly used approach of statistical decisions for the physical layer authenticator faces significant challenges in a dynamically changing, non-stationary environment. To address this problem, this paper introduces a deep learning-based authentication approach to learn and track the variations of channel characteristics, and thus improving the adaptability and convergence of the physical layer authentication. Specifically, an intelligent detection framework based on a Convolutional-Long Short-Term Memory (Convolutional-LSTM) network is designed to deal with channel differences without knowing the statistical properties of the channel. Both the robustness and the detection performance of the learning authentication scheme are analyzed, and extensive simulations and experiments show that the detection accuracy in time-varying environments is significantly improved.

27 July 2023 in Sensors
Verified
Journal Article
Open access
PDF file
XQXiaoying Qiu
Xiaoying Qiu
JYJinwei Yu
Jinwei Yu
WZWenying Zhuang
Wenying Zhuang
GLGuangda Li
Guangda Li
XSXuan Sun
Xuan Sun
The emerging physical-layer unclonable attribute-aided authentication (PLUA) schemes are capable of outperforming traditional isolated approaches, with the advantage of having reliable fingerprints. However, conventional PLUA methods face new challenges in artificial intelligence of things (AIoT) applications owing to their limited flexibility. These challenges arise from the distributed nature of AIoT devices and the involved information, as well as the requirement for short end-to-end latency. To address these challenges, we propose a security authentication scheme that utilizes intelligent prediction mechanisms to detect spoofing attack. Our approach is based on a dynamic authentication method using long short term memory (LSTM), where the edge computing node observes and predicts the time-varying channel information of access devices to detect clone nodes. Additionally, we introduce a Savitzky–Golay filter-assisted high order cumulant feature extraction model (SGF-HOCM) for preprocessing channel information. By utilizing future channel attributes instead of relying solely on previous channel information, our proposed approach enables authentication decisions. We have conducted extensive experiments in actual industrial environments to validate our prediction-based security strategy, which has achieved an accuracy of 97%.