Results 81 to 90 of about 243,531 (318)

An Adversarial Attack via Penalty Method

IEEE Access
Deep learning systems have achieved significant success across various machine learning tasks. However, they are highly vulnerable to attacks. For example, adversarial examples can fool deep learning systems easily by perturbing inputs with small ...
Jiyuan Sun, Haibo Yu, Jianjun Zhao
doaj   +1 more source

Foveation-based Mechanisms Alleviate Adversarial Examples [PDF]

, 2016
We show that adversarial examples, i.e., the visually imperceptible perturbations that result in Convolutional Neural Networks (CNNs) fail, can be alleviated with a mechanism based on foveations---applying the CNN in different image regions. To see this,
Boix, Xavier, Luo, Yan, Poggio, Tomaso, Roig, Gemma, Zhao, Qi   +4 more
core   +1 more source

Spatially Transformed Adversarial Examples

CoRR, 2018
Recent studies show that widely used deep neural networks (DNNs) are vulnerable to carefully crafted adversarial examples. Many advanced algorithms have been proposed to generate adversarial examples by leveraging the $\mathcal{L}_p$ distance for penalizing perturbations.
Chaowei Xiao, Jun-Yan Zhu, Bo Li 0026, Warren He, Mingyan Liu, Dawn Song   +5 more
openaire   +3 more sources

Adversarial Examples: Opportunities and Challenges [PDF]

IEEE Transactions on Neural Networks and Learning Systems, 2019
16 pages, 13 figures, 5 ...
Jiliang Zhang 0002, Chen Li
openaire   +3 more sources

A State‐Adaptive Koopman Control Framework for Real‐Time Deformable Tool Manipulation in Robotic Environmental Swabbing

Advanced Robotics Research, EarlyView.
This work presents a state‐adaptive Koopman linear quadratic regulator framework for real‐time manipulation of a deformable swab tool in robotic environmental sampling. By combining Koopman linearization, tactile sensing, and centroid‐based force regulation, the system maintains stable contact forces and high coverage across flat and inclined surfaces.
Siavash Mahmoudi, Amirreza Davar, Dongyi Wang   +2 more
wiley   +1 more source

Adversarial attack and defense in reinforcement learning-from AI security view

Cybersecurity, 2019
Reinforcement learning is a core technology for modern artificial intelligence, and it has become a workhorse for AI applications ranging from Atrai Game to Connected and Automated Vehicle System (CAV).
Tong Chen, Jiqiang Liu, Yingxiao Xiang, Wenjia Niu, Endong Tong, Zhen Han   +5 more
doaj   +1 more source

Global Feature Attention Network: Addressing the Threat of Adversarial Attack for Aerial Image Semantic Segmentation

Remote Sensing, 2023
Aerial Image Semantic segmentation based on convolution neural networks (CNNs) has made significant process in recent years. Nevertheless, their vulnerability to adversarial example attacks could not be neglected.
Zhen Wang, Buhong Wang, Yaohui Liu, Jianxin Guo   +3 more
doaj   +1 more source

Solid Harmonic Wavelet Bispectrum for Image Analysis

Advanced Science, EarlyView.
The Solid Harmonic Wavelet Bispectrum (SHWB), a rotation‐ and translation‐invariant descriptor that captures higher‐order (phase) correlations in signals, is introduced. Combining wavelet scattering, bispectral analysis, and group theory, SHWB achieves interpretable, data‐efficient representations and demonstrates competitive performance across texture,
Alex Brown, Mathilda Avirett‐Mackenzie, Carolin Villforth, Georgios Exarchakis   +3 more
wiley   +1 more source

An Audio Watermarking Algorithm Based on Adversarial Perturbation

Applied Sciences
Recently, deep learning has been gradually applied to digital watermarking, which avoids the trouble of hand-designing robust transforms in traditional algorithms.
Shiqiang Wu, Jie Liu, Ying Huang, Hu Guan, Shuwu Zhang   +4 more
doaj   +1 more source

Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording Devices [PDF]

, 2021
Stanisław Kacprzak, Konrad Kowalczyk
openalex   +1 more source