AI security for geoscience and remote sensing: Challenges and future trends

Y Xu, T Bai, W Yu, S Chang… - … and Remote Sensing …, 2023 - ieeexplore.ieee.org
Recent advances in artificial intelligence (AI) have significantly intensified research in the
geoscience and remote sensing (RS) field. AI algorithms, especially deep learning-based …

Dual-branch sparse self-learning with instance binding augmentation for adversarial detection in remote sensing images

Z Zhang, X Li, H Li, F Dunkin, B Li… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Remote sensing image analysis technology based on neural networks has significantly
facilitated human life. However, adversarial attacks can drastically impair the performance of …

Threatening patch attacks on object detection in optical remote sensing images

X Sun, G Cheng, L Pei, H Li… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Advanced patch attacks (PAs) on object detection in natural images have pointed out the
great safety vulnerability in methods based on deep neural networks (DNNs). However, little …

Task-specific importance-awareness matters: On targeted attacks against object detection

X Sun, G Cheng, H Li, H Peng… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Targeted Attacks on Object Detection (TAOD) aim to deceive the victim detector into
recognizing a specific instance as the predefined target category while minimizing the …

Robustness of sam: Segment anything under corruptions and beyond

Y Qiao, C Zhang, T Kang, D Kim, C Zhang… - arxiv preprint arxiv …, 2023 - arxiv.org
Segment anything model (SAM), as the name suggests, is claimed to be capable of cutting
out any object and demonstrates impressive zero-shot transfer performance with the …

Boosting knowledge distillation via intra-class logit distribution smoothing

C Li, G Cheng, J Han - … on Circuits and Systems for Video …, 2023 - ieeexplore.ieee.org
Previous arts built an intimate link between knowledge distillation (KD) and label smoothing
(LS) that they both impose regularization on the model training. In this paper, we delve …

A large scale training sample database system for intelligent interpretation of remote sensing imagery

Z Cao, L Jiang, P Yue, J Gong, X Hu, S Liu… - Geo-Spatial …, 2024 - Taylor & Francis
ABSTRACT Artificial Intelligence (AI) Machine Learning (ML) technologies, particularly Deep
Learning (DL), have demonstrated significant potential in the interpretation of Remote …

Adversarial robustness via random projection filters

M Dong, C Xu - Proceedings of the IEEE/CVF Conference …, 2023 - openaccess.thecvf.com
Abstract Deep Neural Networks show superior performance in various tasks but are
vulnerable to adversarial attacks. Most defense techniques are devoted to the adversarial …

A review of surrogate-assisted design optimization for improving urban wind environment

Y Wu, SJ Quan - Building and Environment, 2024 - Elsevier
Improving the urban wind climate yields substantial advantages, encompassing enhanced
public health, increased pedestrian safety, improved building energy efficiency, and effective …

PIHA: Detection method using perceptual image hashing against query-based adversarial attacks

SH Choi, J Shin, YH Choi - Future Generation Computer Systems, 2023 - Elsevier
As a representative adversarial example generation method in a black-box scenario, query-
based adversarial attack has recently been highlighted due to its high attack success rate …