AgriSentinel: Privacy-Enhanced Embedded-LLM Crop Disease Alerting System

2025-09-10

AI Summary

Current AI-based crop disease early-warning systems suffer from data privacy risks, market pricing power monopolies, and high usability barriers for farmers. To address these challenges, this paper proposes a lightweight, privacy-preserving, edge-intelligent, and farmer-centric disease warning system. Our approach innovatively integrates differential privacy with embedded fine-tuning of a lightweight large language model (LLM), enabling on-device sensitive image classification, precise disease identification, and generation of personalized, actionable agronomic recommendations—all without uploading raw data. All computations are executed locally on mobile devices. Experimental results demonstrate that the system achieves >92% classification accuracy under strong privacy guarantees (ε ≤ 1.0) while producing interpretable, operationally relevant recommendations. This work establishes a novel paradigm for secure, autonomous, and deployable intelligent decision support in sustainable agriculture.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Bias, Fairness & Privacy
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Security and privacy of machine learning and AI applications
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Crop diseases pose significant threats to global food security, agricultural productivity, and sustainable farming practices, directly affecting farmers' livelihoods and economic stability. To address the growing need for effective crop disease management, AI-based disease alerting systems have emerged as promising tools by providing early detection and actionable insights for timely intervention. However, existing systems often overlook critical aspects such as data privacy, market pricing power, and farmer-friendly usability, leaving farmers vulnerable to privacy breaches and economic exploitation. To bridge these gaps, we propose AgriSentinel, the first Privacy-Enhanced Embedded-LLM Crop Disease Alerting System. AgriSentinel incorporates a differential privacy mechanism to protect sensitive crop image data while maintaining classification accuracy. Its lightweight deep learning-based crop disease classification model is optimized for mobile devices, ensuring accessibility and usability for farmers. Additionally, the system includes a fine-tuned, on-device large language model (LLM) that leverages a curated knowledge pool to provide farmers with specific, actionable suggestions for managing crop diseases, going beyond simple alerting. Comprehensive experiments validate the effectiveness of AgriSentinel, demonstrating its ability to safeguard data privacy, maintain high classification performance, and deliver practical, actionable disease management strategies. AgriSentinel offers a robust, farmer-friendly solution for automating crop disease alerting and management, ultimately contributing to improved agricultural decision-making and enhanced crop productivity.

Problem

• Addresses crop disease threats to food security and farming
• Solves privacy and economic exploitation in existing AI systems
• Provides on-device disease classification and actionable farmer advice

Innovation

• Differential privacy for sensitive crop data
• Lightweight deep learning for mobile optimization
• On-device LLM for actionable disease suggestions