Results 121 to 130 of about 26,718 (222)

Vision transformers: the threat of realistic adversarial patches

Artificial Intelligence for Security and Defence Applications III
The increasing reliance on machine learning systems has made their security a critical concern. Evasion attacks enable adversaries to manipulate the decision-making processes of AI systems, potentially causing security breaches or misclassification of targets. Vision Transformers (ViTs) have gained significant traction in modern machine learning due to
Cools, Kasper, Maathuis, Clara, van Oers, Alexander M., Hübner, Claudia S., Deligiannis, Nikos, Vandewal, Marijke, De Cubber, Geert   +6 more
openaire   +2 more sources

Deep Learning for Satellite‐Based Forest Disturbance Monitoring: Recent Advances and Challenges

WIREs Data Mining and Knowledge Discovery, Volume 16, Issue 2, June 2026.
Overview of key research challenges in forest disturbance monitoring, including the detection of disturbances of varying severity, the attribution of disturbance agents, and the development of models capable of generalizing across regions. ABSTRACT Climate change and land use pressures are intensifying forest disturbances in many world regions, as ...
Carolina Natel, Christoph Molnar, Ricardo Dalagnol, Peer Nowack   +3 more
wiley   +1 more source

Inferring Internal Structures of Porous Media From Orthogonal External Surfaces: A Novel 2D‐to‐3D Reconstruction Method Based on a Deep Conditional Diffusion Model

Journal of Geophysical Research: Machine Learning and Computation, Volume 3, Issue 3, June 2026.
Abstract Diffusion models, a class of generative models renowned for producing realistic images, hold significant promise for reconstructing complex three‐dimensional (3D) porous media. Nevertheless, existing approaches predominantly generate stochastic microstructures visually resembling the training data but often struggle to accurately recover ...
Yinquan Meng, Jianguo Jiang, Benzhong Zhao, Shujun Ye, Dong Wang, Jichun Wu   +5 more
wiley   +1 more source

Universal attention guided adversarial defense using feature pyramid and non-local mechanisms

Scientific Reports
Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples, significantly hindering the development of deep learning technologies in high-security domains. A key challenge is that current defense methods often lack universality,
Jiawei Zhao, Lizhe Xie, Siqi Gu, Zihan Qin, Yuning Zhang, Zheng Wang, Yining Hu   +6 more
doaj   +1 more source

Characterizing Multi‐Source DNAPL Source Zone Architecture in Channelized Aquifers Using a Geophysics‐Informed Hybrid Deep Learning Framework

Geophysical Research Letters, Volume 53, Issue 10, 28 May 2026.
Abstract Accurate characterization of dense nonaqueous phase liquid (DNAPL) source zone architecture (SZA) is essential for contaminated site remediation. However, highly channelized aquifer heterogeneity and multi‐source contamination pose significant challenges.
Yanhao Wu, Haijian Xie, Manting Ci, Yanghui Shi, Mengcheng Zhang   +4 more
wiley   +1 more source

Computational Modeling Meets 3D Bioprinting: Emerging Synergies in Cardiovascular Disease Modeling

Advanced Healthcare Materials, Volume 15, Issue 17, 8 May 2026.
Emerging advances in three‐dimensional bioprinting and computational modeling are reshaping cardiovascular (CV) research by enabling more realistic, patient‐specific tissue platforms. This review surveys cutting‐edge approaches that merge biomimetic CV constructs with computational simulations to overcome the limitations of traditional models, improve ...
Tanmay Mukherjee, Mehdi Salar Amoli, Sarah Rezapourdamanab, Lama Rita El Shammas, Martin L. Tomov, Emilio A. Mendiola, Vahid Serpooshan, Reza Avazmohammadi   +7 more
wiley   +1 more source

Prompt-Guided Environmentally Consistent Adversarial Patch

CoRR
Adversarial attacks in the physical world pose a significant threat to the security of vision-based systems, such as facial recognition and autonomous driving. Existing adversarial patch methods primarily focus on improving attack performance, but they often produce patches that are easily detectable by humans and struggle to achieve environmental ...
Chaoqun Li, Huanqian Yan, Lifeng Zhou, Tairan Chen, Zhuodong Liu, Hang Su   +5 more
openaire   +2 more sources

VAE+DDPG: An Attention‐Enhanced Variational Autoencoder for Deep Reinforcement Learning‐Based Autonomous Navigation in Low‐Light Environments

Advanced Intelligent Systems, Volume 8, Issue 5, May 2026.
Variational Autoencoder+Deep Deterministic Policy Gradient addresses low‐light failures of infrared depth sensing for indoor robot navigation. Stage 1 pretrains an attention‐enhanced Variational Autoencoder (Convolutional Block Attention Module+Feature Pyramid Network) to map dark depth frames to a well‐lit reconstruction, yielding a 128‐D latent code ...
Uiseok Lee, Chanhong Hwang, Hyunseok Kang, Yechan Park, Hangwoo Jin, Tuan Anh Nguyen, Eunmi Choi, Dugki Min   +7 more
wiley   +1 more source

Cycle Consistent Generative Motion Artifact Correction in Coronary Computed Tomography Angiography

Applied Sciences
In coronary computed tomography angiography (CCTA), motion artifacts due to heartbeats can obscure coronary artery diagnoses. In this study, we introduce a cycle-consistent adversarial-network-based method for motion artifact correction in CCTA.
Amal Muhammad Saleem, Sunghee Jung, Hyuk-Jae Chang, Soochahn Lee   +3 more
doaj   +1 more source

Artificial Intelligence in Autonomous Mobile Robot Navigation: From Classical Approaches to Intelligent Adaptation

Advanced Intelligent Systems, Volume 8, Issue 5, May 2026.
Artificial intelligence (AI) is reshaping autonomous mobile robot navigation beyond classical pipelines. This review analyzes how AI techniques are integrated into core navigation tasks, including path planning and control, localization and mapping, perception, and context‐aware decision‐making. Learning‐based, probabilistic, and soft‐computing methods
Giovanna Guaragnella, Angelo Cardellicchio, Cosimo Patruno, Massimiliano Nitti, Nicola Pedrocchi, Vito Renò   +5 more
wiley   +1 more source