Results 171 to 180 of about 25,829 (292)

Zero Watermarking Using Convolutional Additive Self‐Attention Vision Transformer and Discrete Wavelet Transform‐Variance‐Based Feature Descriptor for Medical Image Security in Mobile Healthcare Services

Advanced Intelligent Systems, EarlyView.
A zero‐watermarking algorithm that combines a refined convolutional additive self‐attention vision transformer (CAS‐ViT) with a discrete wavelet transform variance‐based feature descriptor (DVFD) is proposed for protecting the privacy of medical images in mobile healthcare services.
Pei Liu, Yan Yan, Hao Huang, Ping Wang, Weirong Qin, Xiangjian Zuo, Yongqin Li   +6 more
wiley   +1 more source

Adversarial robustness in deep neural networks based on variable attributes of the stochastic ensemble model. [PDF]

Front Neurorobot, 2023
Qin R, Wang L, Du X, Xie P, Chen X, Yan B.   +5 more
europepmc   +1 more source

Adversarial Erasing Enhanced Multiple Instance Learning (siMILe): Discriminative Identification of Oligomeric Protein Structures in Single Molecule Localization Microscopy

Advanced Intelligent Systems, EarlyView.
Hallgrimson et al. introduce a machine learning algorithm, siMILe, that takes features of single‐molecule localization microscopy localization clusters (e.g., size and sphericity) and finds the clusters that are associated with certain cell conditions (such as differential protein expression or drug treatment).
Christian Hallgrimson, Y. Lydia Li, Claire A. Shou, Ben Cardoen, John Lim, Timothy H. Wong, Ismail M. Khater, Ivan Robert Nabi, Ghassan Hamarneh   +8 more
wiley   +1 more source

Retinal Vessel Segmentation: A Comprehensive Review From Classical Methods to Deep Learning Advances (1982–2025)

Advanced Intelligent Systems, EarlyView.
Four decades of retinal vessel segmentation research (1982–2025) are synthesized, spanning classical image processing, machine learning, and deep learning paradigms. A meta‐analysis of 428 studies establishes a unified taxonomy and highlights performance trends, generalization capabilities, and clinical relevance.
Avinash Bansal, Jan Kubíček, Jana Bahrová, Alice Varyšová, Martin Augustýnek, Marek Penhaker, Juraj Timkovič   +6 more
wiley   +1 more source

Robust Adversarial Example Detection Algorithm Based on High-Level Feature Differences

Sensors
The threat posed by adversarial examples (AEs) to deep learning applications has garnered significant attention from the academic community. In response, various defense strategies have been proposed, including adversarial example detection.
Hua Mu, Chenggang Li, Anjie Peng, Yangyang Wang, Zhenyu Liang   +4 more
doaj   +1 more source

Adversarially Robust Decision Transformer

Advances in Neural Information Processing Systems 37
Accepted to NeurIPS ...
Xiaohang Tang, Afonso Marques, Parameswaran Kamalaruban, Ilija Bogunovic   +3 more
openaire   +3 more sources

Ag/Ag2S Nanoparticle‐Based In‐Materio Lightweight Cryptographic System for IoT Edge Security

Advanced Intelligent Systems, EarlyView.
This work presents a nanomaterial‐based in materio encryption method that directly transforms analog signals through nonlinear Ag/Ag2S nanoparticle networks. By exploiting the inherently nonuniform characteristics that arise from random arrangement of nanoparticles as a unique security key, the approach produces highly complex encrypted waveforms ...
Hiroki Tabata, Yuma Yamashita, Yusuke Nakaoka, Oradee Srikimkaew, Muzhen Xu, Yuki Usami, Shunsuke Araki, Hirofumi Tanaka   +7 more
wiley   +1 more source

Adversarial Attacks Against World Models: Hallucination-Driven Policy Failure

Applied Sciences
World models have demonstrated powerful environment modeling capabilities in scenarios such as autonomous driving and robotics, but their adversarial security issues remain underexplored, in particular, adversarial risk analysis of world models.
Junjian Zhang, Hao Tan, Ruonan Li, Aiping Li, Zhaoquan Gu   +4 more
doaj   +1 more source

Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning. [PDF]

Proc AAAI Conf Artif Intell, 2023
Hong J, Wang H, Wang Z, Zhou J.
europepmc   +1 more source

Evaluating Adversarial Robustness in Simulated Cerebellum

, 2021
It is well known that artificial neural networks are vulnerable to adversarial examples, in which great efforts have been made to improve the robustness.
Chen, Qifeng, Yuezhang, Liu, Li, Bo
core