Results 91 to 100 of about 94,861 (274)

A secure data interaction method based on edge computing

Journal of Cloud Computing: Advances, Systems and Applications
Deep learning achieves an outstanding success in the edge scene due to the appearance of lightweight neural network. However, a number of works show that these networks are vulnerable for adversarial examples, bringing security risks.
Weiwei Miao, Yuanyi Xia, Rui Zhang, Xinjian Zhao, Qianmu Li, Tao Wang, Shunmei Meng   +6 more
doaj   +1 more source

Adversarial Examples with Unlimited Amount of Additions [PDF]

Jisuanji kexue yu tansuo
Malware detection methods based on gray images and deep learning have the characteristics of high detection accuracy and no need of feature engineering. Unfortunately, adversarial examples (AEs) can deceive such detection methods.
JIANG Zhoujie, CHEN Yi, XIONG Ziman, GUO Chun, SHEN Guowei
doaj   +1 more source

Inverse Design of Alloys via Generative Algorithms: Optimization and Diffusion within Learned Latent Space

Advanced Intelligent Discovery, EarlyView.
This work presents a novel generative artificial intelligence (AI) framework for inverse alloy design through operations (optimization and diffusion) within learned compact latent space from variational autoencoder (VAE). The proposed work addresses challenges of limited data, nonuniqueness solutions, and high‐dimensional spaces.
Mohammad Abu‐Mualla, Ellis Crabtree, Fredrick Michael, Yayue Pan, Jida Huang   +4 more
wiley   +1 more source

Adversarial Examples Detection in Features Distance Spaces

, 2019
Maliciously manipulated inputs for attacking machine learning methods -- in particular deep neural networks -- are emerging as a relevant issue for the security of recent artificial intelligence technologies, especially in computer vision. In this paper, we focus on attacks targeting image classifiers implemented with deep neural networks, and we ...
Carrara F, Becarelli R, Caldelli R, Falchi F, Amato G   +4 more
openaire   +3 more sources

Artificial Intelligence for Bone: Theory, Methods, and Applications

Advanced Intelligent Discovery, EarlyView.
Advances in artificial intelligence (AI) offer the potential to improve bone research. The current review explores the contributions of AI to pathological study, biomarker discovery, drug design, and clinical diagnosis and prognosis of bone diseases. We envision that AI‐driven methodologies will enable identifying novel targets for drugs discovery. The
Dongfeng Yuan, Haicang Zhang, Liping Tong, Di Chen   +3 more
wiley   +1 more source

Deep Learning‐Assisted Coherent Raman Scattering Microscopy

Advanced Intelligent Discovery, EarlyView.
The analytical capabilities of coherent Raman scattering microscopy are augmented through deep learning integration. This synergistic paradigm improves fundamental performance via denoising, deconvolution, and hyperspectral unmixing. Concurrently, it enhances downstream image analysis including subcellular localization, virtual staining, and clinical ...
Jianlin Liu, Rujia Liu, Xinyan Zhang, Xun Chen, Shuhua Yue   +4 more
wiley   +1 more source

An adversarial example attack method based on predicted bounding box adaptive deformation in optical remote sensing images [PDF]

PeerJ Computer Science
Existing global adversarial attacks are not applicable to real-time optical remote sensing object detectors based on the YOLO series of deep neural networks, which makes it difficult to improve the adversarial robustness of single-stage detectors.
Leyu Dai, Jindong Wang, Bo Yang, Fan Chen, Hengwei Zhang   +4 more
doaj   +2 more sources

Deep Learning‐Assisted Design of Mechanical Metamaterials

Advanced Intelligent Discovery, EarlyView.
This review examines the role of data‐driven deep learning methodologies in advancing mechanical metamaterial design, focusing on the specific methodologies, applications, challenges, and outlooks of this field. Mechanical metamaterials (MMs), characterized by their extraordinary mechanical behaviors derived from architected microstructures, have ...
Zisheng Zong, Pu Wen, Zhiping Chai, Dunxuan Wu, Han Ding, Zhigang Wu   +5 more
wiley   +1 more source

Detecting Adversarial Examples Using Cross-Modal Semantic Embeddings From Images and Text

IEEE Access
Deep learning models are highly susceptible to adversarial attacks, where subtle perturbations in the input images lead to misclassifications. Adversarial examples typically distort specific features that are critical for accurate image classification ...
Sohee Park, Gwonsang Ryu, Daeseon Choi
doaj   +1 more source

Large Language Model in Materials Science: Roles, Challenges, and Strategic Outlook

Advanced Intelligent Discovery, EarlyView.
Large language models (LLMs) are reshaping materials science. Acting as Oracle, Surrogate, Quant, and Arbiter, they now extract knowledge, predict properties, gauge risk, and steer decisions within a traceable loop. Overcoming data heterogeneity, hallucinations, and poor interpretability demands domain‐adapted models, cross‐modal data standards, and ...
Jinglan Zhang, Xinyi Chen, Xu Ye, Yulin Yang, Bin Ai   +4 more
wiley   +1 more source