Results 11 to 20 of about 3,499,798 (281)
Calibrated Adversarial Training [PDF]
CoRR, 2021 ACML 2021 accepted,24 ...
Tianjin Huang +3 more
core +6 more sources
CAT:Collaborative Adversarial Training [PDF]
CoRR, 2023 Tech ...
Xingbin Liu +4 more
core +4 more sources
Adversarial Training Against Location-Optimized Adversarial Patches [PDF]
, 2020 20 pages, 6 tables, 4 figures, 2 algorithms, European Conference on Computer Vision Workshops ...
Sukrut Rao, David Stutz, Bernt Schiele
core +8 more sources
Masking and Mixing Adversarial Training [PDF]
Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2023 While convolutional neural networks (CNNs) have achieved excellent performances in various computer vision tasks, they often misclassify with malicious samples, a.k.a. adversarial examples. Adversarial training is a popular and straightforward technique to defend against the threat of adversarial examples.
Hiroki Adachi +5 more
core +6 more sources
Phase-shifted Adversarial Training [PDF]
CoRR, 2023 Adversarial training has been considered an imperative component for safely deploying neural network-based applications to the real world. To achieve stronger robustness, existing methods primarily focus on how to generate strong attacks by increasing the number of update steps, regularizing the models with the smoothed loss function, and injecting the
Yeachan Kim +3 more
openaire +4 more sources
Adversarial Training: A Survey [PDF]
CoRRAdversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the effectiveness of AT in improving the robustness of deep neural networks against diverse adversarial attacks. However, a
Mengnan Zhao 0001 +5 more
openaire +3 more sources
Conflict-Aware Adversarial Training
CoRRAdversarial training is the most effective method to obtain adversarial robustness for deep neural networks by directly involving adversarial samples in the training procedure. To obtain an accurate and robust model, the weighted-average method is applied to optimize standard loss and adversarial loss simultaneously.
Zhiyu Xue +3 more
openaire +4 more sources
Neural Networks, 2023 Adversarial robustness is considered as a required property of deep neural networks. In this study, we discover that adversarially trained models might have significantly different characteristics in terms of margin and smoothness, even they show similar robustness.
Hoki Kim +3 more
openaire +4 more sources
Applied Sciences, 2023 While Machine Learning has become the holy grail of modern-day computing, it has many security flaws that have yet to be addressed and resolved. Adversarial attacks are one of these security flaws, in which an attacker appends noise to data samples that ...
Hiskias Dingeto, Juntae Kim
doaj +1 more source
Combining Adversaries with Anti-adversaries in Training
Proceedings of the AAAI Conference on Artificial Intelligence, 2023 Adversarial training is an effective learning technique to improve the robustness of deep neural networks. In this study, the influence of adversarial training on deep learning models in terms of fairness, robustness, and generalization is theoretically investigated under more general perturbation scope that different samples can have different ...
Xiaoling Zhou, Nan Yang, Ou Wu 0001
openaire +4 more sources