Guojia Li

Dr. Guojia Li

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
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.

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

23 September 2025 in Electronics
Verified
Journal Article
Open access
PDF file
明曹明月 曹
明月 曹
GLGuojia Li
Guojia Li
SXSimin Xu
Simin Xu
YZYihong Zhang
Yihong Zhang
YCYan Cao
Yan Cao
Backdoor attacks are recognized as a significant security threat to deep learning. Such attacks can induce models to perform abnormally with inputs that contain predefined triggers, while maintaining state-of-the-art (SOTA) performance on clean data. Research indicates that existing backdoor attacks in the spatial domain have the problems of poor stealthiness and limited effectiveness. Based on the dispersion of adding perturbations in the frequency domain and the idea that multiple frequency-domain transformations can achieve different levels of feature fusion, we propose a dual-frequency-domain transformation backdoor attack method called DFDT (dual-frequency-domain transformation). DFDT executes dual-frequency-domain transformation on both clean samples and a trigger image, then conducts feature fusion in the frequency domain to augment the stealthiness of the poisoned samples. In addition, we introduce regularization samples to reduce the latent separability of clean and poisoned samples. We thoroughly evaluate the DFDT on three image datasets: CIFAR-10, GTSRB, and CIFAR-100. The experimental results show that the DFDT achieves greater stealthiness and effectiveness, achieving an attack success rate (ASR) that approximates 100% and a benign accuracy (BA) nearing 94%. Furthermore, we illustrate that DFDT can successfully evade state-of-the-art defenses, including STRIP, NC, and I-BAU.