PGPradeep Gupta

Pradeep Gupta

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Pradeep Gupta has a total of 52 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    FedPerKD privacy aware personalized federated learning with knowledge distillation for edge oriented tomato leaf disease detection

    by Sonam Gupta, Chin-Shiuh Shieh, Vishal Jain, Mong-Fong Horng, Pradeep Gupta, Satpal Singh Kushwaha

    Tomato leaf diseases threaten global food security by reducing crop yield and quality. Centralized deep-learning detectors require farms to share raw images, which raises privacy, bandwidth, and data-sovereignty concerns. We present FedPer-KD, a privacy-aware federated framework that combines personalization with client-side knowledge distillation: each client keeps its raw images and personalized classifier head locally while the shared MobileNet-V2 feature extractor is aggregated, and a local EfficientNet-B0 teacher supervises the student through softened logits. We evaluate on the PlantVillage tomato leaf dataset (18,345 images, ten classes) using simulated federated clients ( N = 2, 4, 6) trained for 10, 20, and 30 rounds with five random seeds. FedPer-KD reaches 99.34% test accuracy and 99.33% macro-F1 at six clients and 20 rounds while transmitting only the shared base (~ 8.9 MB per client per round, a 36% saving over FedAvg on the same student). Across 2–6 clients it consistently outperforms FedAvg, FedProx, Scaffold, FedPer, FedAvg + KD, and a capacity-matched FedAvg baseline; paired statistical comparisons with Holm-Bonferroni correction confirm significance ( p < 0.05) and Cohen’s d > 1.0 on every comparison. We also report ablations over the Dirichlet heterogeneity parameter (alpha = 0.5, 0.3, 0.1), the teacher fine-tuning schedule, the distillation temperature tau and weight alpha, and a battery of synthetic image corruptions. The framework is privacy-aware rather than formally privacy-preserving, is effective under mild client heterogeneity, and is edge-oriented for downstream deployment.

  • Open Access

    A security aware discrete mathematics framework for Nash-equilibrium based incentive design against selfish mining and validator collusion

    by Satpal Kushwaha, Pradeep Gupta, Lipika Goel, Y. Prasanna, Sonam Gupta

    Blockchain networks depend on incentive mechanisms to ensure that rational miners/validators follow the prescribed consensus protocol. However, strategic behavi...

  • Spectral security analysis of cryptographic Boolean functions using discrete mathematical modelling and machine learning

    by Priya Mathur, Pradeep Gupta, K. Nandhini, Lipika Goel, Satpal Kushwaha, Amit Gupta

    This study investigates how the structural and spectral properties of Boolean functions influence their susceptibility to machine learning–based cryptanalysis....

  • Open Access

    PCE-FL: A Personalized, Clustered, and Communication-Efficient Federated Learning Framework for Robust Tomato Leaf Disease Detection

    by Pradeep Gupta, Sonam Gupta, Lipika Goel, Abhay Kumar Agarwal, Arjun Singh, Vijay Shankar Sharma, Chiranji Lal Chowdhary, Ruchita Chowdhary

    Tomato leaf diseases represent a persistent threat to global food security, causing annual crop losses of 20% to 40%. Although deep learning models achieve accuracies exceeding 95% in centralized settings, their deployment across distributed farms is constrained by data privacy concerns, communication bottlenecks, and heterogeneous data quality. This paper proposes Personalized, Clustered, and Communication-Efficient Federated Learning (PCE-FL), a framework that integrates three synergistic components: (1) server-side client clustering to group farms with similar data distributions for personalized model training; (2) federated knowledge distillation to reduce communication overhead by over 91%; and (3) reputation-based aggregation to ensure robustness against unreliable contributions. Extensive experiments on realistic non-IID simulations of the PlantVillage tomato dataset Dirichlet(α∈{1.0,0.5,0.1}) demonstrate that PCE-FL achieves 89.1% accuracy under extreme heterogeneity (α=0.1), surpassing FedAvg by 10.9 and IFCA by 4.8 percentage points, while maintaining a 91% reduction in communication cost. All improvements are statistically significant (p<0.001). These results advance the practical deployment of privacy-preserving collaborative AI in resource-constrained agricultural environments.

  • Audio Sentiment Analysis Using Dataset Augmentation

    by Mohammad Atif, Mohd Aadil, Khushi Goyal, Himanshi Bharti, Sonam Gupta, Pradeep Gupta

  • Advanced Brain Imaging Analysis for Tumor Detection Using Machine Learning and Deep Learning

    by Harshit, Kushaan Jain, Dhruv Govil, Aditi Gautam, Sonam Gupta, Pradeep Gupta

  • Hybrid Convolutional Neural Network and Generative Adversarial Network Framework for Robust Deepfake Detection: Advancing Accuracy, Scalability, and Multimodal Integration

    by Pradeep Gupta, Sonam Gupta, Lipika Goel, Abhay Kumar Agarwal, Arjun Singh, G. Ramesh

    Deepfakes pose critical threats to digital media integrity and societal trust. This paper presents a hybrid deepfake detection framework combining Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) to address challenges in scalability, generalizability, and adversarial robustness. The framework integrates adversarial training, a temporal decay analysis model, and multimodal detection across audio, video, and text domains. Evaluated on the FaceForensics++ benchmark dataset, the hybrid CNN-GAN model achieved state-of-the-art performance with 98.5% accuracy, 99.1% precision, 97.9% recall, and a Receiver Operating Characteristic-Area Under Curve of 0.995, surpassing conventional models like ResNet50, XceptionNet, and EfficientNet. The temporal analysis component models the decay of deepfake detectability over time, guiding proactive retraining, while the multimodal module identified 97.8% of cross-modal inconsistencies. Simulation of deepfake propagation in social networks revealed significant socio-technical impacts, emphasizing the need for early detection systems and public awareness campaigns to curb misinformation spread. Optimized for real-time deployment, the framework balances high scalability with ethical considerations. This study highlights the importance of interdisciplinary approaches to deepfake detection in advancing AI-driven safeguards for digital ecosystems. Future work will focus on developing lightweight detection models, improving adversarial defenses, and expanding domain-specific applications to enhance the framework's applicability and resilience.


  • JoVE Video Dataset

    by Pradeep Gupta, Sonam Gupta, Lipika Goel, Abhay Kumar Agarwal, Arjun Singh, G. Ramesh

    Deepfakes pose critical threats to digital media integrity and societal trust. This paper presents a hybrid deepfake detection framework combining Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) to address challenges in scalability, generalizability, and adversarial robustness. The framework integrates adversarial training, a temporal decay analysis model, and multimodal detection across audio, video, and text domains. Evaluated on the FaceForensics++ benchmark dataset, the hybrid CNN-GAN model achieved state-of-the-art performance with 98.5% accuracy, 99.1% precision, 97.9% recall, and a Receiver Operating Characteristic-Area Under Curve of 0.995, surpassing conventional models like ResNet50, XceptionNet, and EfficientNet. The temporal analysis component models the decay of deepfake detectability over time, guiding proactive retraining, while the multimodal module identified 97.8% of cross-modal inconsistencies. Simulation of deepfake propagation in social networks revealed significant socio-technical impacts, emphasizing the need for early detection systems and public awareness campaigns to curb misinformation spread. Optimized for real-time deployment, the framework balances high scalability with ethical considerations. This study highlights the importance of interdisciplinary approaches to deepfake detection in advancing AI-driven safeguards for digital ecosystems. Future work will focus on developing lightweight detection models, improving adversarial defenses, and expanding domain-specific applications to enhance the framework's applicability and resilience.

  • Open Access

    AppleVit: A Smart Agricultural Software for Apple Leaf Disease Detection Using AI

    by Pradeep Gupta, Rakesh Singh Jadon

    Apple leaf diseases endanger global apple production at such an intensity that it demands precise detection systems to control disease spread effectively. Traditional inspection methods and Convolutional Neural Network (CNN)-based models face challenges when processing extended image dependencies in leaf images, which subsequently affects their ability to identify diseases accurately. This research develops AppleViT, a lightweight Vision Transformer (ViT)-based model that applies Vision Transformer technology with self-attention approaches to enhance leaf disease classification accuracy and feature extraction within apple leaf detection systems. AppleViT was trained using a public dataset comprising 9,714 apple leaf images, categorized into four classes: Apple Scab, Black Rot, Cedar Apple Rust, and Healthy. The accuracy rate of AppleViT reached 97.8%, which exceeded the ResNet-50 and EfficientNet-B3 and MobileNetV3 models while operating with 1.3 million parameters suitable for precision agriculture real-time usage. The proposed approach demonstrates both high generalization skills alongside precise precision and recall value measurements for disease categories. Future research will create attention visualization features and mobile application compatibility before expanding the architecture to identify multiple diseases across different plant types. AppleViT highlights the potential of Vision Transformer (ViT) technology as a powerful tool to revolutionize plant disease detection for improving crop yield and disease management worldwide.