Md Sabbir Hosen

Dr. Md Sabbir Hosen

School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China
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
3 April 2024 in Electronics
Verified
Journal Article
Open access
PDF file
XCxiaotong cui
xiaotong cui
HZHongxin Zhang
Hongxin Zhang
JXJun Xu
Jun Xu
XFXing Fang
Xing Fang
WNWenxu Ning
Wenxu Ning
Md Sabbir HosenMd Sabbir Hosen
Md Sabbir Hosen
The leaked signals, including electromagnetic, power, timing, and temperature generated during the operation of cryptographic devices, contain highly correlated key value information, leading to security vulnerabilities. In practical operations, due to information collection conditions and time limitations, attackers can only obtain limited valid data. At the same time, the attacker’s data environment cannot be ideal, and noise can affect the acquisition of valid information. Therefore, to improve the effectiveness of obtaining key values from side-channel information analysis in cryptographic devices, we proposed a data augmentation method based on cycle-consistent generative adversarial networks named EME-CycleGAN. By using generators and discriminators, new data are generated to expand the original electromagnetic information dataset, aiming for better modeling effects. For evaluating the data augmentation effect on side-channel electromagnetic signals, we employed the Kolmogorov–Smirnov test to characterize the original and generated data, serving as the evaluation standard for our network model and work. We utilize the existing data to model and verify side-channel attacks, evaluating the impact of the generated information on the overall experimental results. The proposed structure consists of three main parts: side-channel information acquisition, data verification analysis, and determination of attack positions. Experimental results demonstrate that effective attacks on encryption algorithms can be achieved under small-sample dataset conditions.

24 December 2025 in Electronics
Verified
Journal Article
Open access
PDF file
Md Sabbir HosenMd Sabbir Hosen
Md Sabbir Hosen
HZHongxin Zhang
Hongxin Zhang
Early diagnosis of breast and skin cancers significantly reduces mortality rates, yet manual segmentation remains challenging due to subjective interpretation, radiologist fatigue, and irregular lesion boundaries. This study presents BAS-SegNet, a novel boundary-aware segmentation framework that addresses these limitations through an enhanced deep learning architecture. The proposed method integrates three key innovations: (1) an enhanced CNN-based architecture with a switchable feature pyramid interface, a tunable ASPP module, and consistent dropout regularization; (2) an edge-aware preprocessing pipeline using Sobel-based edge magnitude maps stacked as additional channels with geometric augmentations; (3) a boundary-aware hybrid loss combining Binary Cross-Entropy, Dice, and Focal losses with auxiliary edge supervision from morphological gradients. Experimental validation on the BUSI breast ultrasound and ISIC skin lesion datasets demonstrates superior performance, achieving Dice scores of 0.814 and 0.935, respectively, with IoU improvements of 16.3–22.4% for breast cancer and 8.8–11.5% for skin cancer compared with existing methods. The framework shows particular effectiveness under challenging ultrasound conditions where lesion boundaries are ambiguous, offering significant potential for automated clinical diagnosis support.

8 August 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
YWYuanzhen Wang
Yuanzhen Wang
HZHongxin Zhang
Hongxin Zhang
SSShaofei Sun
Shaofei Sun
YMYunfei Ma
Yunfei Ma
XWXiaofeng Wei
Xiaofeng Wei
Md Sabbir HosenMd Sabbir Hosen
Md Sabbir Hosen
In recent years, deep learning methods have become prevalent in the field of side-channel analysis (SCA), leading to a decline in research on nonprofiled attacks and their preprocessing techniques. However, while deep-learning-based SCA methods can reduce the requirements for the quality of leakage signals, they do not fully resolve the need for preprocessing in SCA. Additionally, there is a lack of universal, nontrained preprocessing methods for side-channel leakage under various types of interference. In this article, a new method for preprocessing side channel leakage using synchrosqueezing wavelet transform and ridge energy extraction is proposed to deal with complex scenarios. This method involves two steps: first, applying synchrosqueezing theory to concentrate signal energy in the wavelet domain, and second, utilizing a dynamic path optimization algorithm to locate and extract ridge energy for subsequent attacks. Our proposed solution extracts key information features from the traces, effectively addressing trace distortion caused by varying levels of noise and random disturbances. We validate the effectiveness of our analysis and solution through extensive experiments on four public databases and two self-collected datasets containing power and electromagnetic leakage (EM) from both hardware and software encryption implementations. We compare our experimental results from four indicators: 1) success rate; 2) guessing entropy; 3) signal to noise ratio; and 4) normalized interclass varianc. Besides, we demonstrate the advantages of our method by comparing Measurements to Disclosure and on public datasets. Our method demonstrates significant potential for preprocessing traces in nonprofiled SCA.