Siraj Khan

Dr. Siraj Khan

South China University of Technology, Guangzhou, Guangdong, China
orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
14 October 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Ahmad MusyafaAhmad Musyafa
Ahmad Musyafa
Gao YingGao Ying
Gao Ying
ASAiman Solyman
Aiman Solyman
CWChaojie Wu
Chaojie Wu
Siraj KhanSiraj Khan
Siraj Khan
Grammatical error correction (GEC) is one of the major tasks in natural language processing (NLP) which has recently attracted great attention from researchers. The performance of universal languages such as English and Chinese in the GEC system has improved significantly. This could be attributed to the large number of powerful applications supported by neural network models and pretrained language models. Referring to the satisfactory results of the universal language in the GEC task and the lack of research on the GEC task for low-resource languages, especially Indonesian, this paper proposes an automatic model for Indonesian grammar correction based on the Transformer architecture which can be applied to other low-resource language texts. Furthermore, we build a large corpus of the Indonesian language that can be utilized for evaluating the next Indonesian GEC task. We evaluate the models in this dataset, and the results show that the Transformer-based automatic error correction model achieved significant and satisfactory results compared with the results of previous research models.

20 December 2022 in Computers and Electrical Engineering
Verified
Journal Article
Closed access
Siraj KhanSiraj Khan
Siraj Khan
Muhammad AsimMuhammad Asim
Muhammad Asim
SKSalabat Khan
Salabat Khan
Ahmad MusyafaAhmad Musyafa
Ahmad Musyafa
Qingyao WuQingyao Wu
Qingyao Wu

18 July 2022 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
SKSalabat Khan
Salabat Khan
FLFei Luo
Fei Luo
ZZZijian Zhang
Zijian Zhang
MRMussadiq Abdul Rahim
Mussadiq Abdul Rahim
Siraj KhanSiraj Khan
Siraj Khan
KWKaishun Wu
Kaishun Wu
Vehicular social networking is expected to become a reality soon, where secure and privacy-preserving identity management is a prerequisite. Various organizations and studies have recommended using Vehicular Public-key Infrastructure (VPKI) to securely and privately manage vehicles' identities. However, the existing VPKI schemes still do not deal with identity management in vehicular social networking. In this work, we propose a Privacy-Preserving Identity Management (PPTIM) scheme for vehicular social networking to securely and privately manage vehicles' social identities. PPTIM builds on the transparency log (distributed ledger) proposals for web PKI, but it addresses challenges specific to vehicular social networking. All pseudo-social identities, pseudonym certificates issued against pseudo-social identities, revocation process, and revocation status validation are conducted on a transparency log. With an efficient data structure named the Accumulation Tree (AT), we extend the conventional transparency log to offer trustworthy pseudonym certificate validation without relying on the Certificate Revocation Lists (CRLs). In addition, PPTIM strengthens the security of vehicular social networking by protecting vehicles to a greater extent from being duped by malicious pseudonym certificates through logging and constant monitoring. Finally, performance and security analysis show the cost-effectiveness and security of PPTIM.

2 February 2024 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
Siraj KhanSiraj Khan
Siraj Khan
PYPengshuai Yin
Pengshuai Yin
YGYuxin Guo
Yuxin Guo
Muhammad AsimMuhammad Asim
Muhammad Asim
AEAhmed Abd El-Latif
Ahmed Abd El-Latif

2 May 2025 in IEEE Access
Verified
Journal Article
Open access
MAMohammad Iqbal Saryuddin Assaqty
Mohammad Iqbal Saryuddin Assaqty
Gao YingGao Ying
Gao Ying
AAAbeer D. Algarni
Abeer D. Algarni
Siraj KhanSiraj Khan
Siraj Khan
MCMohuya Chakraborty
Mohuya Chakraborty
SASadique Ahmad
Sadique Ahmad
The complexity of the entire process of supply chain management (SCM) is quite cumbersome and traditional way of handling it is devoid of proper authentication and security and very often suffers from human errors in dealing with flaws in quality control process of SCM. While it may have started with shipment tracking, the outcome of using IoT on supply chains has spread to every link in the chain. For instance, manufacturers are employing Internet-enabled sensors in production to find product faults, resulting in higher-quality production runs. Physical Unclonable Function (PUF) is a security mechanism that exploits the unique, unrepeatable physical characteristics of hardware components to generate distinct cryptographic keys or identifiers, typically for a semiconductor device like an Internet of Things (IoT) device. The unique identification of IoT devices along the supply chain is implemented by using PUFs as tamper-resistant IDs. Blockchain, the distributed, immutable ledger, on the other hand is the disruptive technology that provides higher security as compared to traditional centralized systems. The integration of PUF and blockchain proves to be quite interesting while handling the above issues of authentication. A smart contract on the blockchain is a software code that executes spontaneously as and when the conditions of the contract or agreement are satisfied. Hence after authentication process the results are fed to blockchain smart contract for the final validation. This paper presents a novel permissioned blockchain smart contract-based lightweight authentication scheme for SCM using PUF of IoT known as SPUFChain. Informal and formal security analysis (using AVISPA and BAN logic) of the proposed framework show its potential to combat several attack scenarios like man-in-the middle, non-repudiation, impersonation, replay attacks and many other security features as compared to other related schemes. The processing time (~13.8ms) is better than existing lightweight scheme for blockchain-based SCM as well.

28 May 2023 in Symmetry
Verified
Journal Article
Open access
PDF file
Siraj KhanSiraj Khan
Siraj Khan
Muhammad AsimMuhammad Asim
Muhammad Asim
SCSamia Allaoua Chelloug
Samia Allaoua Chelloug
BABasma Abdelrahiem
Basma Abdelrahiem
SKSalabat Khan
Salabat Khan
Ahmad MusyafaAhmad Musyafa
Ahmad Musyafa
Unsupervised domain adaptation (UDA) is a popular approach to reducing distributional discrepancies between labeled source and the unlabeled target domain (TD) in machine learning. However, current UDA approaches often align feature distributions between two domains explicitly without considering the target distribution and intra-domain category information, potentially leading to reduced classifier efficiency when the distribution between training and test sets differs. To address this limitation, we propose a novel approach called Cluster Matching-based Improved Kernel Fisher criterion (CM-IKFC) for object classification in image analysis using machine learning techniques. CM-IKFC generates accurate pseudo-labels for each target sample by considering both domain distributions. Our approach employs K-means clustering to cluster samples in the latent subspace in both domains and then conducts cluster matching in the TD. During the model component training stage, the Improved Kernel Fisher Criterion (IKFC) is presented to extend cluster matching and preserve the semantic structure and class transitions. To further enhance the performance of the Kernel Fisher criterion, we use a normalized parameter, due to the difficulty in solving the characteristic equation that draws inspiration from symmetry theory. The proposed CM-IKFC method minimizes intra-class variability while boosting inter-class variants in all domains. We evaluated our approach on benchmark datasets for UDA tasks and our experimental findings show that CM-IKFC is superior to current state-of-the-art methods.