Results 91 to 100 of about 173,113 (165)

Detecting Audio Adversarial Examples in Automatic Speech Recognition Systems Using Decision Boundary Patterns. [PDF]

J Imaging, 2022
Zong W, Chow YW, Susilo W, Kim J, Le NT.
europepmc   +1 more source

Universal adversarial examples and perturbations for quantum classifiers. [PDF]

Natl Sci Rev, 2022
Gong W, Deng DL.
europepmc   +1 more source

Universal adversarial defense in remote sensing based on pre-trained denoising diffusion models

International Journal of Applied Earth Observations and Geoinformation
Deep neural networks (DNNs) have risen to prominence as key solutions in numerous AI applications for earth observation (AI4EO). However, their susceptibility to adversarial examples poses a critical challenge, compromising the reliability of AI4EO ...
Weikang Yu, Yonghao Xu, Pedram Ghamisi
doaj   +1 more source

Generating adversarial examples without specifying a target model. [PDF]

PeerJ Comput Sci, 2021
Yang G, Li M, Fang X, Zhang J, Liang X.
europepmc   +1 more source

Beware the Black-Box: On the Robustness of Recent Defenses to Adversarial Examples. [PDF]

Entropy (Basel), 2021
Mahmood K, Gurevin D, van Dijk M, Nguyen PH.   +3 more
europepmc   +1 more source

Improving the Transferability of Adversarial Examples With a Noise Data Enhancement Framework and Random Erasing. [PDF]

Front Neurorobot, 2021
Xie P, Shi S, Yang S, Qiao K, Liang N, Wang L, Chen J, Hu G, Yan B.   +8 more
europepmc   +1 more source

POSES: Patch Optimization Strategies for Efficiency and Stealthiness Using eXplainable AI

IEEE Access
Adversarial examples, which are carefully crafted inputs designed to deceive deep learning models, create significant challenges in Artificial Intelligence.
Han-Ju Lee, Jin-Seoung Kim, Han-Jin Lee, Seok-Hwan Choi   +3 more
doaj   +1 more source

Adversarial Example Generation Method Based on Wavelet Transform

Information
Adversarial examples are crucial tools for assessing the robustness of deep neural networks (DNNs) and revealing potential security vulnerabilities.
Meng Bi, Xiaoguo Liang, Baiyu Wang, Longxin Liu, Xin Yin, Jiafeng Liu   +5 more
doaj   +1 more source

Targeted Discrepancy Attacks: Crafting Selective Adversarial Examples in Graph Neural Networks

IEEE Access
In this study, we present a novel approach to adversarial attacks for graph neural networks (GNNs), specifically addressing the unique challenges posed by graphical data.
Hyun Kwon, Jang-Woon Baek
doaj   +1 more source

Developing Hessian–Free Second–Order Adversarial Examples for Adversarial Training

International Journal of Applied Mathematics and Computer Science
Recent studies show that deep neural networks (DNNs) are extremely vulnerable to elaborately designed adversarial examples. Adversarial training, which uses adversarial examples as training data, has been proven to be one of the most effective methods of
Qian Yaguan, Zhang Liangjian, Wang Yuqi, Ji Boyuan, Yao Tengteng, Wang Bin   +5 more
doaj   +1 more source