Results 101 to 110 of about 29,955 (264)

Machine Learning Interatomic Potentials for Energy Materials: Architectures, Training Strategies, and Applications

Advanced Energy Materials, EarlyView.
Machine learning interatomic potentials bridge quantum accuracy and computational efficiency for materials discovery. Architectures from Gaussian process regression to equivariant graph neural networks, training strategies including active learning and foundation models, and applications in solid‐state electrolytes, batteries, electrocatalysts ...
In Kee Park, Saeed Pourasad, Jinhong Mun, Arunkumar Chitteth Rajan, Tae Hyeon Park, Anand Rohit, Mohammad Zafari, Tan‐Lien Pham, Eunjae Jung, Bonseung Koo, Miran Ha, Gi Beom Sim, Hyun Gyu Park, Won Woong Choi, Kwanghyeon Jo, Soohaeng Yoo Willow, David ChangMo Yang, Chang Woo Myung, Geunsik Lee, Kwang S. Kim   +19 more
wiley   +1 more source

Measuring the Transferability of Adversarial Examples

CoRR, 2019
Adversarial examples are of wide concern due to their impact on the reliability of contemporary machine learning systems. Effective adversarial examples are mostly found via white-box attacks. However, in some cases they can be transferred across models, thus enabling them to attack black-box models.
Deyan Petrov, Timothy M. Hospedales
openaire   +2 more sources

From Top to Bottom: Manufacturing Process‐Context Aware Resolution of Energy Device Electrodes Through a 3D Diffusion Generative Model

Advanced Energy Materials, EarlyView.
The application of a generative diffusion model, enhanced with a training data augmentation pipeline retaining the manufacturing process context of electrode microstructures, leads to improved fidelity of the through‐plane tortuosity factor in the AI generated samples.
Victor Ramirez‐Camacho, Siwar Ben Hadj Ali, Maxence Desnoyers, Francisco Fernandez, Nassima Benammar, Alejandro A. Franco   +5 more
wiley   +1 more source

Ranking the Transferability of Adversarial Examples

ACM Transactions on Intelligent Systems and Technology
Adversarial transferability in blackbox scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they lack assurance on whether these examples will successfully compromise the target model. Until now, the prevalent method to ascertain success has been trial and error—testing crafted samples ...
Moshe Levy, Guy Amit, Yuval Elovici, Yisroel Mirsky   +3 more
openaire   +2 more sources

Real‐Time Multicolor Fluorescence Microscopy via Cross‐Channel Acquisition and Deep‐Learning‐Based Inference

Advanced Intelligent Discovery, EarlyView.
Sequential multicolor fluorescence imaging in dynamic microsystems is constrained by acquisition speed and excitation dose. This study introduces a real‐time framework to reconstruct spectrally separated channels from reduced cross‐channel acquisitions (frames containing mixed spectral contributions).
Juan J. Huaroto, Yuxin Jin, Nicholas Roy, Sarthak Misra   +3 more
wiley   +1 more source

High-frequency Feature Masking-based Adversarial Attack Algorithm [PDF]

Jisuanji kexue
Deep neural networks have achieved widespread application in the field of imagerecognition,however,their complex structures make them vulnerable to adversarial attacks.Constructing adversarial examples that are imperceptible to the human eye is crucial ...
WANG Liuyi, ZHOU Chun, ZENG Wenqiang, HE Xingxing, MENG Hua
doaj   +1 more source

Image Adversarial Example Generation Method Based on Adaptive Parameter Adjustable Differential Evolution. [PDF]

Entropy (Basel), 2023
Lin Z, Peng C, Tan W, He X.
europepmc   +1 more source

Adversarial Examples Are Not Bugs, They Are Superposition

CoRR
Adversarial examples -- inputs with imperceptible perturbations that fool neural networks -- remain one of deep learning's most perplexing phenomena despite nearly a decade of research. While numerous defenses and explanations have been proposed, there is no consensus on the fundamental mechanism.
Liv Gorton, Owen Lewis
openaire   +2 more sources

Cell Segmentation Beyond 2D—A Review of the State‐of‐the‐Art

Advanced Intelligent Discovery, EarlyView.
Cell segmentation underpins many biological image analysis tasks, yet most deep learning methods remain limited to 2D despite the inherently 3D nature of cellular processes. This review surveys segmentation approaches beyond 2D, comparing 2.5D and fully 3D methods, analyzing 31 models and 32 volumetric datasets, and introducing a unified reference ...
Fabian Schmeisser, Haseeb Muhammad, Junaid Younas, Gillian Lovell, Bianca Migliori, Andreas Dengel, Sheraz Ahmed   +6 more
wiley   +1 more source

Research on Image Adversarial Example Generation Method Based on SE-AdvGAN [PDF]

Jisuanji gongcheng
Adversarial examples are crucial for evaluating the robustness of Deep Neural Network (DNN) and revealing their potential security risks. The adversarial example generation method based on a Generative Adversarial Network (GAN), AdvGAN, has made ...
ZHAO Hong, SONG Furong, LI Wengai
doaj   +1 more source