Results 21 to 30 of about 215,342 (268)
Gray-Box Adversarial Training [PDF]
, 2018 Adversarial samples are perturbed inputs crafted to mislead the machine learning systems. A training mechanism, called adversarial training, which presents adversarial samples along with clean samples has been introduced to learn robust models. In order to scale adversarial training for large datasets, these perturbations can only be crafted using fast
B. S. Vivek +2 more
openaire +2 more sources
Modeling Adversarial Noise for Adversarial Training
, 2021 Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks. Motivated by the fact that adversarial noise contains well-generalizing features and that the relationship between adversarial data and natural data can help infer natural data and make reliable ...
Zhou, Dawei +3 more
openaire +2 more sources
Adversarial momentum-contrastive pre-training
Pattern Recognition Letters, 2022 Comment: 8 pages;
Cong Xu, Dan Li, Min Yang
openaire +2 more sources
Calibrated Adversarial Training
, 2021 ACML 2021 accepted,24 ...
Huang, Tianjin +3 more
openaire +3 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 Methods for Deep Learning: A Systematic Review
Algorithms, 2022 Deep neural networks are exposed to the risk of adversarial attacks via the fast gradient sign method (FGSM), projected gradient descent (PGD) attacks, and other attack algorithms.
Weimin Zhao +2 more
doaj +1 more source
Adversarial Training for Sketch Retrieval [PDF]
, 2016 Generative Adversarial Networks (GAN) are able to learn excellent representations for unlabelled data which can be applied to image generation and scene classification. Representations learned by GANs have not yet been applied to retrieval. In this paper, we show that the representations learned by GANs can indeed be used for retrieval.
Creswell, A, Bharath, AA
openaire +3 more sources
A3T: accuracy aware adversarial training
Machine Learning, 2023 AbstractAdversarial training has been empirically shown to be more prone to overfitting than standard training. The exact underlying reasons are still not fully understood. In this paper, we identify one cause of overfitting related to current practices of generating adversarial examples from misclassified samples.
Enes Altinisik +3 more
openaire +3 more sources
Dual Head Adversarial Training [PDF]
2021 International Joint Conference on Neural Networks (IJCNN), 2021 Deep neural networks (DNNs) are known to be vulnerable to adversarial examples/attacks, raising concerns about their reliability in safety-critical applications. A number of defense methods have been proposed to train robust DNNs resistant to adversarial attacks, among which adversarial training has so far demonstrated the most promising results ...
Jiang, Yujing +3 more
openaire +2 more sources
Deep Learning Based Robust Text Classification Method via Virtual Adversarial Training
IEEE Access, 2020 The existing methods of generating adversarial texts usually change the original meanings of texts significantly and even generate the unreadable texts.
Wei Zhang, Qian Chen, Yunfang Chen
doaj +1 more source