Results 31 to 40 of about 3,499,798 (281)
Exploring generative adversarial networks and adversarial training
International Journal of Cognitive Computing in Engineering, 2022 Recognized as a realistic image generator, Generative Adversarial Network (GAN) occupies a progressive section in deep learning. Using generative modeling, the underlying generator model learns the real target distribution and outputs fake samples from ...
Afia Sajeeda, B M Mainul Hossain, Ph.D
doaj +1 more source
Probabilistic Categorical Adversarial Attack & Adversarial Training
CoRR, 2022 The existence of adversarial examples brings huge concern for people to apply Deep Neural Networks (DNNs) in safety-critical tasks. However, how to generate adversarial examples with categorical data is an important problem but lack of extensive exploration.
Xu, Han +6 more
openaire +3 more sources
Towards Adversarial Robustness for Multi-Mode Data through Metric Learning
Sensors, 2023 Adversarial attacks have become one of the most serious security issues in widely used deep neural networks. Even though real-world datasets usually have large intra-variations or multiple modes, most adversarial defense methods, such as adversarial ...
Sarwar Khan +3 more
doaj +1 more source
Pre-Trained Adversarial Perturbations
Advances in Neural Information Processing Systems 35, 2022 Self-supervised pre-training has drawn increasing attention in recent years due to its superior performance on numerous downstream tasks after fine-tuning. However, it is well-known that deep learning models lack the robustness to adversarial examples, which can also invoke security issues to pre-trained models, despite being less explored.
Yuanhao Ban, Yinpeng Dong
openaire +4 more sources
Universal Adversarial Training
Proceedings of the AAAI Conference on Artificial Intelligence, 2020 Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels. In contrast, a universal perturbation is an update that can be added to any image in a broad class of images, while still changing the predicted class label.
Ali Shafahi +5 more
openaire +5 more sources
An Extended Study of Human-like Behavior under Adversarial Training
, 2023 Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable to humans and ...
Gavrikov, Paul +2 more
core +1 more source
Training Neural Networks with Random Noise Images for Adversarial Robustness
, 2021 Despite their high accuracy, deep neural networks (DNNs) are vulnerable to adversarial examples. Currently, adversarial training is the mainstream defense approach against adversarial examples.
Jixue Liu +7 more
core +1 more source
A3T: Adversarially Augmented Adversarial Training
CoRR, 2018 accepted for an oral presentation in Machine Deception Workshop, NIPS ...
Akram Erraqabi +3 more
openaire +2 more sources
A Survey on Efficient Methods for Adversarial Robustness
IEEE Access, 2022 Deep learning has revolutionized computer vision with phenomenal success and widespread applications. Despite impressive results in complex problems, neural networks are susceptible to adversarial attacks: small and imperceptible changes in input space ...
Awais Muhammad, Sung-Ho Bae
doaj +1 more source
Adversarial Training for Free!
CoRR, 2019 ISBN:978-1-7138-0793 ...
Ali Shafahi +8 more
openaire +4 more sources