LeafyVGG-16: Transfer Learning for Plant Disease Detection with Cyber Risk Analysis

Abstract

Plant disease detection using deep learning is essential for precision agriculture, enabling early and automated crop health monitoring. This study proposes an end-to-end transfer learning pipeline, LeafyVGG-16, for multi-class classification of plant diseases and nutrient deficiencies using a tomato leaf dataset. The framework integrates data preprocessing, augmentation, and a VGG-16 backbone with a two-stage fine-tuning strategy. The proposed model is evaluated against CNN, DenseNet-121, Inception-V3, EfficientNetB0, and ResNet-50, achieving an accuracy of 0.93 with precision, recall, and F1-scores of 0.93, 0.90, and 0.92, respectively. These results demonstrate the effectiveness of transfer learning for fine-grained plant disease recognition. We further evaluate model robustness under adversarial cyber attacks to assess deployment reliability in agricultural systems. Under Fast Gradient Sign Method (FGSM) attacks ( ϵ = 0.01– 0.05), the model shows an accuracy drop of 1%–7.5%, while Projected Gradient Descent (PGD) attacks ( ϵ = 0.05, step size = 0.005, 10 iterations) produce similar degradation, highlighting the model’s vulnerability to adversarial perturbations. These findings highlight potential security and reliability risks in AI-based agricultural decision-making systems. Future work will focus on improving robustness and cyber-resilience and extending this framework to other crops for secure and context-aware deployment in resource-constrained environments.

Plant phenotyping relevance

植物葉の画像から病害・栄養欠乏状態を分類する深層学習パイプラインが研究の中心であり、複数モデルとの比較評価と敵対的攻撃下での頑健性検証も実施しているため。

Code and data availability

The paper's plant-phenotyping input is the publicly available Tomato-Village Variant-a dataset (4,525 tomato leaf images across 8 disease/deficiency classes), which the authors explicitly cite with a public Kaggle URL. No author analysis code, trained model checkpoints, or supplementary data deposits are mentioned. The