AI security for geoscience and remote sensing: Challenges and future trends
Recent advances in artificial intelligence (AI) have significantly intensified research in the
geoscience and remote sensing (RS) field. AI algorithms, especially deep learning-based …
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
Remote sensing image analysis technology based on neural networks has significantly
facilitated human life. However, adversarial attacks can drastically impair the performance of …
facilitated human life. However, adversarial attacks can drastically impair the performance of …
Threatening patch attacks on object detection in optical remote sensing images
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 …
great safety vulnerability in methods based on deep neural networks (DNNs). However, little …
Task-specific importance-awareness matters: On targeted attacks against object detection
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 …
recognizing a specific instance as the predefined target category while minimizing the …
Robustness of sam: Segment anything under corruptions and beyond
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 …
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 …
(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
ABSTRACT Artificial Intelligence (AI) Machine Learning (ML) technologies, particularly Deep
Learning (DL), have demonstrated significant potential in the interpretation of Remote …
Learning (DL), have demonstrated significant potential in the interpretation of Remote …
Adversarial robustness via random projection filters
Abstract Deep Neural Networks show superior performance in various tasks but are
vulnerable to adversarial attacks. Most defense techniques are devoted to the adversarial …
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 …
public health, increased pedestrian safety, improved building energy efficiency, and effective …
PIHA: Detection method using perceptual image hashing against query-based adversarial attacks
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 …
based adversarial attack has recently been highlighted due to its high attack success rate …