Adversarial Robustness of Vision-Based Perception in Precision Agriculture: Attacks, Defenses, and a Case Study on the Agrosense v2 Platform

Smart Agricultural Technology一手来源 · 原始研究11月1日 · 周日阅读 0

核心看点

系统梳理农业视觉感知的对抗攻击与防御并给出平台案例，属细分领域方法性研究，有专业参考价值但产业影响有限。

关注点

该研究以Agrosense v2平台为案例，梳理农业视觉感知模型在对抗攻击下的脆弱性与防御手段，可为部署视觉识别系统的精准农业场景提供安全评估参考，结论适用性受平台与作物条件限制。

发布主体的原始资料；自述数据与结论仍以原文限定为准。

论文信息

Hari Krishna Parvatham / Shiyu Liu / Yiannis Ampatzidis 等 4 人

Smart Agricultural Technology

DOI: 10.1016/j.atech.2026.102697

论文摘要

Adversarial Robustness of Vision-Based Perception in Precision Agriculture: Attacks, Defenses, and a Case Study on the Agrosense v2 Platform。Smart Agricultural Technology

论文原文与出版信息

Smart Agricultural Technology

查看论文原文

继续探索

技术

农业人工智能计算机视觉精准农业

其他

智慧农业对抗鲁棒性

论文信息

论文摘要

继续探索

技术

其他

相关检索

相关阅读

The Evolution of Precision Agriculture

农田用上了“AI大脑”——探访天津智慧农业未来农场管控平台

Robust and transparent crop-row detection from RGB field imagery for vision-based agricultural guidance systems

PLANT-GPK v2.7: Spatial Heterogeneity and Predictive Digital Twin for Plant Phenotyping

Entomopathogenic nematode recent applications in precision agriculture: Methods, challenges, and future perspectives

[预印本]植物病害数据集的数据中心综述:分类、关键分析、环境变异性与精准农业启示(A Data-Centric Review of Plant Disease Datasets: Taxonomy, Critical Analysis, Environmental Variability, and Implications for Precision Agriculture)

A hybrid PCA and 1D-CNN approach with regional priors for accurate agricultural monitoring: a case study with EuroCropsML

A Comprehensive Review of Deep Learning in Agricultural Visual Perception: Progress, Bottlenecks, and Emerging Trends (深度学习在农业视觉感知中的综合综述:进展、瓶颈与新兴趋势)

PIPNet EA for Robust and Explainable Crop Weed Classification Using Enhanced Prototype Evidence Aggregation

IMPLEMENTATION OF META-HEURISTIC OPTIMIZATION ALGORITHMS IN CONVOLUTIONAL NEURAL NETWORKS FOR OBJECT DETECTION AND CLASSIFICATION

Hybrid transformer and CNN for hyperspectral image classification with spectral band selection

Smart Agriculture Technology: A Review of Robotic Platforms, Sensing Modalities, Artificial Intelligence, Datasets, Evaluation Metrics, and Future Research Directions

Improving early season crop type mapping using machine learning algorithms with combined SAR and optical time series

WeedNet: a foundation model-based global-to-local AI approach for weed species identification and classification