Zunera Jalil
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zunera Jalil has a total of 87 co-authors. Here are the top co-authors by number of shared publications:
- Abdul Rehman Javed
Department of Cyber Security, Air University, Islamabad 44000, Pakistan
18 shared publications Anwar M. Mirza
Department of Computer Science, FAST National University of Computer and Emerging Sciences, A.K.Brohi Road, Sector H-11/4, Islamabad, Pakistan
6 shared publications- Thippa Reddy Gadekallu
Lovely Professional University
5 shared publications - Farkhund Iqbal
Zayed University
4 shared publications - Celestine Iwendi
University of Bolton, UK
3 shared publications - Natalia Kryvinska
Department of Information Management and Business Systems, Faculty of Management, Comenius University Bratislava, Bratislava, Slovakia
3 shared publications
Latest Publications
- Open Access
- 1 July 2026
- Published by Walter de Gruyter GmbH in Journal of Information Assurance and Security
- Vol. 21 (3) , 119-136
Towards Automated Identification of Block Cipher Structures Using Machine Learning
This paper focuses on the classification of block ciphers based on their structure, which is a crucial step in automated cryptanalysis. For this purpose, five machine learning algorithms, including Logistic Regression, Naive Bayes, k-Nearest Neighbour, Random Forest, and XGBoost, are applied to ciphertext data to differentiate between Substitution–Permutation Networks (SPN) and Feistel block cypher structures. A comprehensive experimental framework is developed using 16 block ciphers, including AES, DES, Blowfish, Twofish, and Camelia, etc evaluated across two encryption modes (ECB and CBC) with 5-fold cross validation under four different scenarios. To improve generalization and eliminate dataset bias, ciphertext datasets are generated using fixed key and multiple random keys and diverse plaintext sources, including text, source code, and binary data. A feature extraction pipeline based on byte-level statistics, compression characteristics, and higher-order histogram features is employed, followed by classification using five machine learning and one deep learning models. NIST SP800-22 suite tests were conducted on ciphertext dataset. Results confirmed that despite ciphertexts exhibit near-ideal entropy and pass standard randomness tests; however, small higher-order statistical deviations remain observable. Experimental results demonstrate that these weak statistical signals can be leveraged to achieve classification accuracies exceeding 90% for ciphertext, with performance increasing as ciphertext size increases. The classification accuracy is highest for ECB and decreases for CBC, consistent with increasing diffusion and inter-block dependency. Feature importance and ablation studies further reveal that statistical features provide the dominant discriminative signal. These findings highlight the presence of finite-sample statistical artifacts that can be detected using machine learning, and provide new insights into the intersection of statistical cryptanalysis and machine learning, with implications for automated cryptographic analysis.
- 1 July 2026
- Published by Walter de Gruyter GmbH in Journal of Information Assurance and Security
- Vol. 21 (3) , 119-136
Open AccessTowards Automated Identification of Block Cipher Structures Using Machine Learning
This paper focuses on the classification of block ciphers based on their structure, which is a crucial step in automated cryptanalysis. For this purpose, five machine learning algorithms, including Logistic Regression, Naive Bayes, k-Nearest Neighbour, Random Forest, and XGBoost, are applied to ciphertext data to differentiate between Substitution–Permutation Networks (SPN) and Feistel block cypher structures. A comprehensive experimental framework is developed using 16 block ciphers, including AES, DES, Blowfish, Twofish, and Camelia, etc evaluated across two encryption modes (ECB and CBC) with 5-fold cross validation under four different scenarios. To improve generalization and eliminate dataset bias, ciphertext datasets are generated using fixed key and multiple random keys and diverse plaintext sources, including text, source code, and binary data. A feature extraction pipeline based on byte-level statistics, compression characteristics, and higher-order histogram features is employed, followed by classification using five machine learning and one deep learning models. NIST SP800-22 suite tests were conducted on ciphertext dataset. Results confirmed that despite ciphertexts exhibit near-ideal entropy and pass standard randomness tests; however, small higher-order statistical deviations remain observable. Experimental results demonstrate that these weak statistical signals can be leveraged to achieve classification accuracies exceeding 90% for ciphertext, with performance increasing as ciphertext size increases. The classification accuracy is highest for ECB and decreases for CBC, consistent with increasing diffusion and inter-block dependency. Feature importance and ablation studies further reveal that statistical features provide the dominant discriminative signal. These findings highlight the presence of finite-sample statistical artifacts that can be detected using machine learning, and provide new insights into the intersection of statistical cryptanalysis and machine learning, with implications for automated cryptographic analysis.
- 27 September 2024
- Published by Springer Nature in Journal of Computer Virology and Hacking Techniques
- Vol. 20 (4) , 867-884
RansomGuard: a framework for proactive detection and mitigation of cryptographic windows ransomware
- 27 September 2024
- Published by Springer Nature in Journal of Computer Virology and Hacking Techniques
- Vol. 20 (4) , 867-884
RansomGuard: a framework for proactive detection and mitigation of cryptographic windows ransomware
- Open Access
- 12 September 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (11) , 1-15
Data Augmentation-based Novel Deep Learning Method for Deepfaked Images Detection
Recent advances in artificial intelligence have led to deepfake images, enabling users to replace a real face with a genuine one. deepfake images have recently been used to malign public figures, politicians, and even average citizens. deepfake but realistic images have been used to stir political dissatisfaction, blackmail, propagate false news, and even carry out bogus terrorist attacks. Thus, identifying real images from fakes has got more challenging. To avoid these issues, this study employs transfer learning and data augmentation technique to classify deepfake images. For experimentation, 190,335 RGB-resolution deepfake and real images and image augmentation methods are used to prepare the dataset. The experiments use the deep learning models: convolutional neural network (CNN), Inception V3, visual geometry group (VGG19), and VGG16 with a transfer learning approach. Essential evaluation metrics (accuracy, precision, recall, F1-score, confusion matrix, and AUC-ROC curve score) are used to test the efficacy of the proposed approach. Results revealed that the proposed approach achieves an accuracy, recall, F1-score and AUC-ROC score of 90% and 91% precision, with our fine-tuned VGG16 model outperforming other DL models in recognizing real and deepfakes.
- 12 September 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (11) , 1-15
Open AccessData Augmentation-based Novel Deep Learning Method for Deepfaked Images Detection
Recent advances in artificial intelligence have led to deepfake images, enabling users to replace a real face with a genuine one. deepfake images have recently been used to malign public figures, politicians, and even average citizens. deepfake but realistic images have been used to stir political dissatisfaction, blackmail, propagate false news, and even carry out bogus terrorist attacks. Thus, identifying real images from fakes has got more challenging. To avoid these issues, this study employs transfer learning and data augmentation technique to classify deepfake images. For experimentation, 190,335 RGB-resolution deepfake and real images and image augmentation methods are used to prepare the dataset. The experiments use the deep learning models: convolutional neural network (CNN), Inception V3, visual geometry group (VGG19), and VGG16 with a transfer learning approach. Essential evaluation metrics (accuracy, precision, recall, F1-score, confusion matrix, and AUC-ROC curve score) are used to test the efficacy of the proposed approach. Results revealed that the proposed approach achieves an accuracy, recall, F1-score and AUC-ROC score of 90% and 91% precision, with our fine-tuned VGG16 model outperforming other DL models in recognizing real and deepfakes.
- Top Cited PapersOpen Access
- 7 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 23 (8) , 1-19
Multimodal Religiously Hateful Social Media Memes Classification Based on Textual and Image Data
Multimodal hateful social media meme detection is an important and challenging problem in the vision-language domain. Recent studies show high accuracy for such multimodal tasks due to datasets that provide better joint multimodal embedding to narrow the semantic gap. Religiously hateful meme detection is not extensively explored among published datasets. While there is a need for higher accuracy on religiously hateful memes, deep learning–based models often suffer from inductive bias. This issue is addressed in this work with the following contributions. First, a religiously hateful memes dataset is created and published publicly to advance hateful religious memes detection research. Over 2000 meme images are collected with their corresponding text. The proposed approach compares and fine-tunes VisualBERT pre-trained on the Conceptual Caption (CC) dataset for the downstream classification task. We also extend the dataset with the Facebook hateful memes dataset. We extract visual features using ResNeXT-152 Aggregated Residual Transformations–based Masked Regions with Convolutional Neural Networks (R-CNN) and Bidirectional Encoder Representations from Transformers (BERT) uncased for textual encoding for the early fusion model. We use the primary evaluation metric of an Area Under the Operator Characters Curve (AUROC) to measure model separability. Results show that the proposed approach has a higher AUROC score of 78%, proving the model’s higher separability performance and an accuracy of 70%. It shows comparatively superior performance considering dataset size and against ensemble-based machine learning approaches.
- 7 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 23 (8) , 1-19
Top Cited PapersOpen AccessMultimodal Religiously Hateful Social Media Memes Classification Based on Textual and Image Data
Multimodal hateful social media meme detection is an important and challenging problem in the vision-language domain. Recent studies show high accuracy for such multimodal tasks due to datasets that provide better joint multimodal embedding to narrow the semantic gap. Religiously hateful meme detection is not extensively explored among published datasets. While there is a need for higher accuracy on religiously hateful memes, deep learning–based models often suffer from inductive bias. This issue is addressed in this work with the following contributions. First, a religiously hateful memes dataset is created and published publicly to advance hateful religious memes detection research. Over 2000 meme images are collected with their corresponding text. The proposed approach compares and fine-tunes VisualBERT pre-trained on the Conceptual Caption (CC) dataset for the downstream classification task. We also extend the dataset with the Facebook hateful memes dataset. We extract visual features using ResNeXT-152 Aggregated Residual Transformations–based Masked Regions with Convolutional Neural Networks (R-CNN) and Bidirectional Encoder Representations from Transformers (BERT) uncased for textual encoding for the early fusion model. We use the primary evaluation metric of an Area Under the Operator Characters Curve (AUROC) to measure model separability. Results show that the proposed approach has a higher AUROC score of 78%, proving the model’s higher separability performance and an accuracy of 70%. It shows comparatively superior performance considering dataset size and against ensemble-based machine learning approaches.
- RetractionOpen Access
- 28 August 2023
- Published by Springer Nature in Personal and Ubiquitous Computing
- Vol. 28 (S1) , 23
Retraction Note: An optimised homomorphic CRT-RSA algorithm for secure and efficient communication
- 28 August 2023
- Published by Springer Nature in Personal and Ubiquitous Computing
- Vol. 28 (S1) , 23
RetractionOpen AccessRetraction Note: An optimised homomorphic CRT-RSA algorithm for secure and efficient communication
- Top Cited PapersOpen Access
- 21 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 134018-134028
Deepfake Audio Detection via MFCC Features Using Machine Learning
Deepfake content is created or altered synthetically using artificial intelligence (AI) approaches to appear real. It can include synthesizing audio, video, images, and text. Deepfakes may now produce natural-looking content, making them harder to identify. Much progress has been achieved in identifying video deepfakes in recent years; nevertheless, most investigations in detecting audio deepfakes have employed the ASVSpoof or AVSpoof dataset and various machine learning, deep learning, and deep learning algorithms. This research uses machine and deep learning-based approaches to identify deepfake audio. Mel-frequency cepstral coefficients (MFCCs) technique is used to acquire the most useful information from the audio. We choose the Fake-or-Real dataset, which is the most recent benchmark dataset. The dataset was created with a text-to-speech model and is divided into four sub-datasets: for-rece, for-2-sec, for-norm and for-original . These datasets are classified into sub-datasets mentioned above according to audio length and bit rate. The experimental results show that the support vector machine (SVM) outperformed the other machine learning (ML) models in terms of accuracy on for-rece and for-2-sec datasets, while the gradient boosting model performed very well using for-norm dataset. The VGG-16 model produced highly encouraging results when applied to the for-original dataset. The VGG-16 model outperforms other state-of-the-art approaches.
- 21 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 134018-134028
Top Cited PapersOpen AccessDeepfake Audio Detection via MFCC Features Using Machine Learning
Deepfake content is created or altered synthetically using artificial intelligence (AI) approaches to appear real. It can include synthesizing audio, video, images, and text. Deepfakes may now produce natural-looking content, making them harder to identify. Much progress has been achieved in identifying video deepfakes in recent years; nevertheless, most investigations in detecting audio deepfakes have employed the ASVSpoof or AVSpoof dataset and various machine learning, deep learning, and deep learning algorithms. This research uses machine and deep learning-based approaches to identify deepfake audio. Mel-frequency cepstral coefficients (MFCCs) technique is used to acquire the most useful information from the audio. We choose the Fake-or-Real dataset, which is the most recent benchmark dataset. The dataset was created with a text-to-speech model and is divided into four sub-datasets: for-rece, for-2-sec, for-norm and for-original . These datasets are classified into sub-datasets mentioned above according to audio length and bit rate. The experimental results show that the support vector machine (SVM) outperformed the other machine learning (ML) models in terms of accuracy on for-rece and for-2-sec datasets, while the gradient boosting model performed very well using for-norm dataset. The VGG-16 model produced highly encouraging results when applied to the for-original dataset. The VGG-16 model outperforms other state-of-the-art approaches.
- Open Access
- 12 August 2022
- Published by Hindawi Limited in Computational Intelligence and Neuroscience
- Vol. 2022, 1-12
A Novel Benchmark Dataset for COVID-19 Detection during Third Wave in Pakistan
Coronavirus (COVID-19) is a highly severe infection caused by the severe acute respiratory coronavirus 2 (SARS-CoV-2). The polymerase chain reaction (PCR) test is essential to confirm the COVID-19 infection, but it has certain limitations, including paucity of reagents, is computationally time-consuming, and requires expert clinicians. Clinicians suggest that the PCR test is not a reliable automated COVID-19 patient detection system. This study proposed a machine learning-based approach to evaluate the PCR role in COVID-19 detection. We collect real data containing 603 COVID-19 samples from the Pakistan Institute of Medical Sciences (PIMS) Hospital in Islamabad, Pakistan, during the third COVID-19 wave. The experiments are separated into two sets. The first set comprises 24 features, including PCR test results, whereas the second comprises 24 features without PCR test. The findings demonstrate that the decision tree achieves the best detection rate for positive and negative COVID-19 patients in both scenarios. The findings reveal that PCR does not contribute to detecting COVID-19 patients. The findings also aid in the early detection of COVID-19, mainly when PCR test results are insufficient for diagnosing COVID-19 and help developing countries with a paucity of PCR tests and specialist facilities.
- 12 August 2022
- Published by Hindawi Limited in Computational Intelligence and Neuroscience
- Vol. 2022, 1-12
Open AccessA Novel Benchmark Dataset for COVID-19 Detection during Third Wave in Pakistan
Coronavirus (COVID-19) is a highly severe infection caused by the severe acute respiratory coronavirus 2 (SARS-CoV-2). The polymerase chain reaction (PCR) test is essential to confirm the COVID-19 infection, but it has certain limitations, including paucity of reagents, is computationally time-consuming, and requires expert clinicians. Clinicians suggest that the PCR test is not a reliable automated COVID-19 patient detection system. This study proposed a machine learning-based approach to evaluate the PCR role in COVID-19 detection. We collect real data containing 603 COVID-19 samples from the Pakistan Institute of Medical Sciences (PIMS) Hospital in Islamabad, Pakistan, during the third COVID-19 wave. The experiments are separated into two sets. The first set comprises 24 features, including PCR test results, whereas the second comprises 24 features without PCR test. The findings demonstrate that the decision tree achieves the best detection rate for positive and negative COVID-19 patients in both scenarios. The findings reveal that PCR does not contribute to detecting COVID-19 patients. The findings also aid in the early detection of COVID-19, mainly when PCR test results are insufficient for diagnosing COVID-19 and help developing countries with a paucity of PCR tests and specialist facilities.
- Open Access
- 11 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 38885-38894
A Large-Scale Benchmark Dataset for Anomaly Detection and Rare Event Classification for Audio Forensics
With the emergence of new digital technologies, a significant surge has been seen in the volume of multimedia data generated from various smart devices. Several challenges for data analysis have emerged to extract useful information from multimedia data. One such challenge is the early and accurate detection of anomalies in multimedia data. This study proposes an efficient technique for anomaly detection and classification of rare events in audio data. In this paper, we develop a vast audio dataset containing seven different rare events (anomalies) with 15 different background environmental settings (e.g., beach, restaurant, and train) to focus on both detection of anomalous audio and classification of rare sound (e.g., events—baby cry, gunshots, broken glasses, footsteps) events for audio forensics. The proposed approach uses the supreme feature extraction technique by extracting mel-frequency cepstral coefficients (MFCCs) features from the audio signals of the newly created dataset and selects the minimum number of best-performing features for optimum performance using principal component analysis (PCA). These features are input to state-of-the-art machine learning algorithms for performance analysis. We also apply machine learning algorithms to the state-of-the-art dataset and realize good results. Experimental results reveal that the proposed approach effectively detects all anomalies and superior performance to existing approaches in all environments and cases.
- 11 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 38885-38894
Open AccessA Large-Scale Benchmark Dataset for Anomaly Detection and Rare Event Classification for Audio Forensics
With the emergence of new digital technologies, a significant surge has been seen in the volume of multimedia data generated from various smart devices. Several challenges for data analysis have emerged to extract useful information from multimedia data. One such challenge is the early and accurate detection of anomalies in multimedia data. This study proposes an efficient technique for anomaly detection and classification of rare events in audio data. In this paper, we develop a vast audio dataset containing seven different rare events (anomalies) with 15 different background environmental settings (e.g., beach, restaurant, and train) to focus on both detection of anomalous audio and classification of rare sound (e.g., events—baby cry, gunshots, broken glasses, footsteps) events for audio forensics. The proposed approach uses the supreme feature extraction technique by extracting mel-frequency cepstral coefficients (MFCCs) features from the audio signals of the newly created dataset and selects the minimum number of best-performing features for optimum performance using principal component analysis (PCA). These features are input to state-of-the-art machine learning algorithms for performance analysis. We also apply machine learning algorithms to the state-of-the-art dataset and realize good results. Experimental results reveal that the proposed approach effectively detects all anomalies and superior performance to existing approaches in all environments and cases.
- Top Cited PapersOpen Access
- 12 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 11065-11089
A Comprehensive Survey on Computer Forensics: State-of-the-Art, Tools, Techniques, Challenges, and Future Directions
With the alarmingly increasing rate of cybercrimes worldwide, there is a dire need to combat cybercrimes timely and effectively. Cyberattacks on computing machines leave certain artifacts on target device storage that can reveal the identity and behavior of cyber-criminals if processed and analyzed intelligently. Forensic agencies and law enforcement departments use several digital forensic toolkits, both commercial and open-source, to examine digital evidence. The proposed research survey focuses on identifying the current state-of-the-art digital forensics concepts in existing research, sheds light on research gaps, presents a detailed introduction of different computer forensic domains and forensic toolkits used for computer forensics in the current era. The proposed survey also presents a comparative analysis based on the tool’s characteristics to facilitate investigators in tool selection during the forensics process. Finally, the proposed survey identifies and derives current challenges and future research directions in computer forensics.
- 12 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 11065-11089
Top Cited PapersOpen AccessA Comprehensive Survey on Computer Forensics: State-of-the-Art, Tools, Techniques, Challenges, and Future Directions
With the alarmingly increasing rate of cybercrimes worldwide, there is a dire need to combat cybercrimes timely and effectively. Cyberattacks on computing machines leave certain artifacts on target device storage that can reveal the identity and behavior of cyber-criminals if processed and analyzed intelligently. Forensic agencies and law enforcement departments use several digital forensic toolkits, both commercial and open-source, to examine digital evidence. The proposed research survey focuses on identifying the current state-of-the-art digital forensics concepts in existing research, sheds light on research gaps, presents a detailed introduction of different computer forensic domains and forensic toolkits used for computer forensics in the current era. The proposed survey also presents a comparative analysis based on the tool’s characteristics to facilitate investigators in tool selection during the forensics process. Finally, the proposed survey identifies and derives current challenges and future research directions in computer forensics.