Baysah Guwor
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Baysah Guwor has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Mohammad Shabaz
Marwadi University
2 shared publications - S. Silvia Priscila
Bharath Institute of Higher Education and Research, India
2 shared publications - Dharmendrasinh D. Zala
Marwadi University
1 shared publication - Kishan Makadiya
Marwadi University
1 shared publication R. Sridaran
1 shared publication- Rijwan Khan
Marwadi University, India
1 shared publication
Latest Publications
- Open Access
- 14 July 2026
- Published by MDPI AG in Multimedia
- Vol. 2 (3) , 11
Multi-Modal Deep Learning for Image Forgery Detection: A Synergistic Fusion Approach Combining Visual Artifacts and Metadata Consistency Analysis
Multimedia data have been continuously increasing in magnitude, and so has the sophistication of manipulation methods, thereby making the digital forensic investigation process more complicated. The easy access to sophisticated image editing software and AI-generated materials has brought up the issue of information integrity, the reliability of legal evidence, and public trust. Traditional image forensics methods are usually concerned with either the detection of visual artifacts based on convolutional neural networks (CNNs) or based on metadata analysis, frequently independently of each other. This paper presents a multi-modal fusion paradigm, comprising visual feature-based feature extraction and metadata inconsistency-based detectors, to improve the classification strength. A two-stream design is used, comprising a high-level visual artifact capturing the transfer learning-based MobileNetV2 network and an XGBoost classifier that analyses EXIF metadata discrepancies. The heterogeneous representations are merged in a feature-level fusion strategy to generate a final authenticity prediction. It was tested on individual datasets and a compiled dataset of 26,023 images from CoMoFoD, CG-1050 and CASIA v1 and v2. The suggested approach had an overall accuracy of 83.85%, which was higher than the visual-only (68.61%) and metadata-only (75.85%) baselines. These findings show that complementary visual and metadata cues are much more useful in detection, while the use of a lightweight backbone enables efficient, high-throughput forensic analysis suitable for real-world deployment.
- 14 July 2026
- Published by MDPI AG in Multimedia
- Vol. 2 (3) , 11
Open AccessMulti-Modal Deep Learning for Image Forgery Detection: A Synergistic Fusion Approach Combining Visual Artifacts and Metadata Consistency Analysis
Multimedia data have been continuously increasing in magnitude, and so has the sophistication of manipulation methods, thereby making the digital forensic investigation process more complicated. The easy access to sophisticated image editing software and AI-generated materials has brought up the issue of information integrity, the reliability of legal evidence, and public trust. Traditional image forensics methods are usually concerned with either the detection of visual artifacts based on convolutional neural networks (CNNs) or based on metadata analysis, frequently independently of each other. This paper presents a multi-modal fusion paradigm, comprising visual feature-based feature extraction and metadata inconsistency-based detectors, to improve the classification strength. A two-stream design is used, comprising a high-level visual artifact capturing the transfer learning-based MobileNetV2 network and an XGBoost classifier that analyses EXIF metadata discrepancies. The heterogeneous representations are merged in a feature-level fusion strategy to generate a final authenticity prediction. It was tested on individual datasets and a compiled dataset of 26,023 images from CoMoFoD, CG-1050 and CASIA v1 and v2. The suggested approach had an overall accuracy of 83.85%, which was higher than the visual-only (68.61%) and metadata-only (75.85%) baselines. These findings show that complementary visual and metadata cues are much more useful in detection, while the use of a lightweight backbone enables efficient, high-throughput forensic analysis suitable for real-world deployment.
- 1 April 2026
- Published by Springer Nature
- p. 3-29
Taxonomy of Tools and Techniques for Cyber Forensic Investigations
- 1 April 2026
- Published by Springer Nature
- p. 3-29
Taxonomy of Tools and Techniques for Cyber Forensic Investigations
- Open Access
- 2 March 2026
- Published by Springer Nature
Reliability and Completeness of Metadata Extraction Tools in Image-Based Forensic Analysis
Digital images serve as a vital source of evidence in forensic investigations, containing metadata that can reveal timestamps, device characteristics, geolocation details, and editing history. However, this metadata is highly vulnerable to alteration, removal, and degradation during routine handling, thereby creating challenges in maintaining authenticity and evidentiary reliability. This study evaluates the integrity and performance of open-source metadata extraction tools to support more accurate and trustworthy forensic analysis. The research process consisted of two stages. The first stage assessed the forensic soundness of five widely used tools by verifying that metadata extraction did not alter the original files. The second stage examined their accuracy, completeness, and resilience across various image transformations using a custom dataset across 10 metadata fields. The result shows that although all tools preserved evidence integrity, their ability to recover metadata varied considerably, with fragile fields such as Unique Image ID and location information poorly recovered. Among the tested tools, Exif Tool demonstrated the most balanced performance across accuracy (95.8%), completeness (64.3%), and efficiency. This study provides practical guidance for investigators, forensic educators, and tool developers by highlighting the strengths and limitations of these solutions. Its findings support enhanced forensic training and the development of more reliable open-source metadata extraction tools and methodologies to strengthen the admissibility and credibility of image-based digital evidence.
- 2 March 2026
- Published by Springer Nature
Open AccessReliability and Completeness of Metadata Extraction Tools in Image-Based Forensic Analysis
Digital images serve as a vital source of evidence in forensic investigations, containing metadata that can reveal timestamps, device characteristics, geolocation details, and editing history. However, this metadata is highly vulnerable to alteration, removal, and degradation during routine handling, thereby creating challenges in maintaining authenticity and evidentiary reliability. This study evaluates the integrity and performance of open-source metadata extraction tools to support more accurate and trustworthy forensic analysis. The research process consisted of two stages. The first stage assessed the forensic soundness of five widely used tools by verifying that metadata extraction did not alter the original files. The second stage examined their accuracy, completeness, and resilience across various image transformations using a custom dataset across 10 metadata fields. The result shows that although all tools preserved evidence integrity, their ability to recover metadata varied considerably, with fragile fields such as Unique Image ID and location information poorly recovered. Among the tested tools, Exif Tool demonstrated the most balanced performance across accuracy (95.8%), completeness (64.3%), and efficiency. This study provides practical guidance for investigators, forensic educators, and tool developers by highlighting the strengths and limitations of these solutions. Its findings support enhanced forensic training and the development of more reliable open-source metadata extraction tools and methodologies to strengthen the admissibility and credibility of image-based digital evidence.
- 13 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Standards Magazine
- Vol. PP (24712825) , 1-12
GAS4SEC: Toward a Secure and Optimized Smart Contract for Digital Chain of Custody in Digital Forensics
It is evident that blockchain offers strong guarantees of integrity and transparency for handling digital evidence; however, its practical adoption has remained a challenge due to factors such as privacy, deployment constraints, and admissibility issues in the real word environment. This study, therefore, proposes GAS4SEC, a framework for designing, validating, and deploying a secure, cost effective, and forensically sound blockchain-based evidence management system. The system combines formally bound smart contract architecture with role-based access control, record of immutable evidences and custody processes to maintain authenticity, traceability and accountability. In order to overcome the security risks and challenges, the research includes the systematic vulnerability analysis correlated with the OWASP smart contract risks to make sure that unauthorized access, logic abuse, and invalid state transitions are addressed. A validation-based process of development imposes forensic invariants and security guarantees across the lifetime of a contract, and controlled gas optimization is used to achieve better deployment without affecting the evidentiary integrity. The proposed system is deployed and tested on the Polygon Layer-2 blockchain, with functional testing, security testing, gas testing, and stress testing with evidence operations and role change concurrency. The experiment proves that the approach can be used to achieve scalable and cost-effective on-chain forensics operations without sacrificing the high levels of security assistance and forensic integrity and proves to be applicable to the management of digital evidence in practice.
- 13 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Standards Magazine
- Vol. PP (24712825) , 1-12
GAS4SEC: Toward a Secure and Optimized Smart Contract for Digital Chain of Custody in Digital Forensics
It is evident that blockchain offers strong guarantees of integrity and transparency for handling digital evidence; however, its practical adoption has remained a challenge due to factors such as privacy, deployment constraints, and admissibility issues in the real word environment. This study, therefore, proposes GAS4SEC, a framework for designing, validating, and deploying a secure, cost effective, and forensically sound blockchain-based evidence management system. The system combines formally bound smart contract architecture with role-based access control, record of immutable evidences and custody processes to maintain authenticity, traceability and accountability. In order to overcome the security risks and challenges, the research includes the systematic vulnerability analysis correlated with the OWASP smart contract risks to make sure that unauthorized access, logic abuse, and invalid state transitions are addressed. A validation-based process of development imposes forensic invariants and security guarantees across the lifetime of a contract, and controlled gas optimization is used to achieve better deployment without affecting the evidentiary integrity. The proposed system is deployed and tested on the Polygon Layer-2 blockchain, with functional testing, security testing, gas testing, and stress testing with evidence operations and role change concurrency. The experiment proves that the approach can be used to achieve scalable and cost-effective on-chain forensics operations without sacrificing the high levels of security assistance and forensic integrity and proves to be applicable to the management of digital evidence in practice.