Yan Cao

Prof. Yan Cao

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
29 October 2025 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
HJHaoyang Jia
Haoyang Jia
XXXiaobing Xiong
Xiaobing Xiong
HLHaibin Luo
Haibin Luo
YCYan Cao
Yan Cao
Modern vehicles rely on the Controller Area Network (CAN) for inter-module communication, yet its inherent lack of security exposes it to cyber-attacks that can compromise vehicle safety. Among these, stealthy attacks, such as masquerade and sophisticated injection attacks, are particularly pernicious as they mimic normal traffic patterns, evading many conventional detection systems. To address this critical challenge, this paper introduces DriveShield, a novel unsupervised intrusion detection framework designed to unmask such evasive threats. The core of DriveShield is its unique approach to adversarial spatiotemporal feature learning. It begins by fusing granular time-interval data with physical signal data to create a rich, comprehensive representation of network behavior. This fused data is then fed into an adversarial autoencoder, which is trained not only to precisely reconstruct normal data but also to fool a discriminator. This adversarial process compels the model to learn the intricate, underlying distribution of legitimate traffic, making it highly sensitive to subtle anomalies that signal an attack. Extensive experiments on public CAN datasets demonstrate that DriveShield significantly outperforms state-of-the-art methods, especially in its ability to identify complex, stealthy attacks. This research provides a robust defense mechanism for in-vehicle networks, advancing the state of automotive cybersecurity against modern, adaptive threats.

29 October 2025 in Electronics
Verified
Journal Article
Open access
PDF file
GLGuojia Li
Guojia Li
明曹明月 曹
明月 曹
YZYihong Zhang
Yihong Zhang
SXSimin Xu
Simin Xu
YCYan Cao
Yan Cao
Deep neural networks have demonstrated remarkable performance in object detection tasks; however, they remain highly susceptible to adversarial attacks. Previous surveys in computer vision have provided considerable coverage of physical adversarial attacks, yet the aspect of systematically categorizing and evaluating their physical deployment methods for object detection has not received commensurate focus. To address this gap, we categorize physical adversarial attacks into three primary classes based on the physical deployment of adversarial patterns: manipulating 2D physical objects, injecting adversarial signals, and placing 3D adversarial camouflage. These categories are further analyzed and compared across nine key attributes. Furthermore, we elucidate the relationship between physical adversarial attacks against object detection models and two critical properties: transferability and perceptibility. Our findings indicate that while attacks involving the manipulation of 2D physical objects are relatively straightforward to deploy, their adversarial patterns are often perceptible to human observers. Similarly, 3D adversarial camouflage tends to lack stealthiness, whereas adversarial signal injection offers stronger imperceptibility. However, all three attack types exhibit limited transferability across different models and modalities. Finally, we discuss current challenges and propose actionable directions for future research, aiming to foster the development of more robust object detection systems.

23 October 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
YHYong Huang
Yong Huang
WWWenjing Wang
Wenjing Wang
DZDalong Zhang
Dalong Zhang
JWJunjie Wang
Junjie Wang
CCChen Chen
Chen Chen
WWWei Wang
Wei Wang
Radio frequency (RF) fingerprinting techniques provide a promising supplement to cryptography-based approaches but rely on dedicated equipment to capture in-phase and quadrature (IQ) samples, hindering their wide adoption. Recent advances advocate easily obtainable channel state information (CSI) by commercial WiFi devices for lightweight RF fingerprinting, while falling short in addressing the challenges of coarse granularity of CSI measurements in an open-world setting. In this article, we propose CSI2Q, a novel CSI fingerprinting system that achieves comparable performance to IQ-based approaches. Instead of extracting fingerprints directly from raw CSI measurements, CSI2Q first transforms frequency-domain CSI measurements into time-domain signals that share the same feature space with IQ samples. Then, we employ a deep auxiliary learning strategy to transfer useful knowledge from an IQ fingerprinting model to the CSI counterpart. Finally, the trained CSI model is combined with an OpenMax function to estimate the likelihood of unknown ones. We evaluate CSI2Q on one synthetic CSI dataset involving 85 devices and two real CSI datasets, including 10 and 25 WiFi routers, respectively. Our system achieves accuracy increases of at least 16% on the synthetic CSI dataset, 20% on the in-lab CSI dataset, and 17% on the in-the-wild CSI dataset.

11 February 2026 in Expert Systems with Applications
Verified
Journal Article
Closed access
HJHaoyang Jia
Haoyang Jia
XXXiaobing Xiong
Xiaobing Xiong
HLHaibin Luo
Haibin Luo
YCYan Cao
Yan Cao

6 July 2025 in Electronics
Verified
Journal Article
Open access
PDF file
YZYihong Zhang
Yihong Zhang
GLGuojia Li
Guojia Li
YZYihui Zhang
Yihui Zhang
YCYan Cao
Yan Cao
明曹明月 曹
明月 曹
CXChengyao Xue
Chengyao Xue
Backdoor attacks in self-supervised learning pose an increasing threat. Recent studies have shown that knowledge distillation can mitigate these attacks by altering feature representations. In response, we propose BASK, a novel backdoor attack that remains effective after distillation. BASK uses feature weighting and representation alignment strategies to implant persistent backdoors into the encoder’s feature space. This enables transferability to student models. We evaluated BASK on the CIFAR-10 and STL-10 datasets and compared it with existing self-supervised backdoor attacks under four advanced defenses: SEED, MKD, Neural Cleanse, and MiMiC. Our experimental results demonstrate that BASK maintains high attack success rates while preserving downstream task performance. This highlights the robustness of BASK and the limitations of current defense mechanisms.

13 December 2025 in Neurocomputing
Verified
Journal Article
Open access
SXSimin Xu
Simin Xu
GLGuojia Li
Guojia Li
MCMingyue Cao
Mingyue Cao
YZYihong Zhang
Yihong Zhang
YCYan Cao
Yan Cao