Results 141 to 150 of about 173,113 (165)

Adversarial Examples for Hamming Space Search

IEEE Transactions on Cybernetics, 2020
Due to its strong representation learning ability and its facilitation of joint learning for representation and hash codes, deep learning-to-hash has achieved promising results and is becoming increasingly popular for the large-scale approximate nearest neighbor search.
Erkun Yang, Tongliang Liu, Cheng Deng, Dacheng Tao   +3 more
openaire   +4 more sources

Principal Component Adversarial Example

IEEE Transactions on Image Processing, 2020
Despite having achieved excellent performance on various tasks, deep neural networks have been shown to be susceptible to adversarial examples, i.e., visual inputs crafted with structural imperceptible noise. To explain this phenomenon, previous works implicate the weak capability of the classification models and the difficulty of the classification ...
Yonggang Zhang, Xinmei Tian, Ya Li, Xinchao Wang, Dacheng Tao   +4 more
openaire   +2 more sources

Learning Universal Adversarial Perturbation by Adversarial Example

Proceedings of the AAAI Conference on Artificial Intelligence, 2022
Deep learning models have shown to be susceptible to universal adversarial perturbation (UAP), which has aroused wide concerns in the community. Compared with the conventional adversarial attacks that generate adversarial samples at the instance level, UAP can fool the target model for different instances with only a single perturbation, enabling us to
Maosen Li, Yanhua Yang, Kun Wei, Xu Yang, Heng Huang   +4 more
openaire   +1 more source

Adversarial Examples in Arabic

2019 International Conference on Computational Science and Computational Intelligence (CSCI), 2019
Several studies have shown that deep neural networks (DNNs) are vulnerable to adversarial examples - perturbed inputs that cause DNN-based models to produce incorrect outputs. A variety of adversarial attacks have been proposed in the domains of computer vision and natural language processing (NLP); however, most attacks in the NLP domain have been ...
Basemah Alshemali, Jugal Kalita
openaire   +1 more source

Revealing Perceptual Proxies with Adversarial Examples

IEEE Transactions on Visualization and Computer Graphics, 2021
Data visualizations convert numbers into visual marks so that our visual system can extract data from an image instead of raw numbers. Clearly, the visual system does not compute these values as a computer would, as an arithmetic mean or a correlation. Instead, it extracts these patterns using perceptual proxies; heuristic shortcuts of the visual marks,
Brian D, Ondov, Fumeng, Yang, Matthew, Kay, Niklas, Elmqvist, Steven, Franconeri   +4 more
openaire   +2 more sources

Advops: Decoupling Adversarial Examples

Pattern Recognition, 2023
Donghua Wang, Wen Yao, Tingsong Jiang, Xiaoqian Chen   +3 more
openaire   +1 more source

Rethinking Adversarial Examples

Traditionally, adversarial examples have been defined as imperceptible perturbations that fool deep neural networks. This thesis challenges this view by examining unrestricted adversarial examples – a broader class of manipulations that can compromise model security while preserving semantics.
openaire   +1 more source

Adversarial examples: A survey

2018 Baltic URSI Symposium (URSI), 2018
Adversarial examples are a phenomenon that have gathered a lot of attention in recent studies. The fact that the addition of very small, but carefully crafted perturbations to the inputs of sophisticated and high performing machine learning models may cause them to make significant errors, is both fascinating and important.
openaire   +1 more source

A Survey of Adversarial Attack and Defense Methods for Malware Classification in Cyber Security

IEEE Communications Surveys and Tutorials, 2023
Senming Yan, Jing Ren, Wei Wang
exaly  

Interpreting Adversarial Examples in Deep Learning: A Review

ACM Computing Surveys, 2023
Sicong Han, Chenhao Lin, Chao Shen
exaly