.png){kind=icon}
Return
Strengthening Robustness Under Adversarial Attacks Using Brain Visual Codes
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2022.3204995.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The vulnerability of computational models to adversarial examples highlights the differences in the ways humans and machines process visual information. Motivated by human perception invariance in object recognition, we aim to incorporate human brain representations for training a neural network. We propose a multi-modal approach that integrates visual input and the corresponding encoded brain signals to improve the adversarial robustness of the model. We investigate the effects of visual attacks of various strengths on an image classification task. Our experiments show that the proposed multi-modal framework achieves more robust performance against the increasing amount of adversarial perturbation than the baseline methods. Remarkably, in a black-box setting, our framework achieves a performance improvement of at least 7.54% and 5.97% on the MNIST and CIFAR-10 datasets, respectively. Finally, we conduct an ablation study to justify the necessity and significance of incorporating visual brain representations.
Keywords:
Visualization
Functional magnetic resonance imaging
Brain modeling
Robustness
Perturbation methods
Training data
Decoding
Neural networks
Computational modeling
Adversarial defense
brain decoding
deep neural network
fMRI
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W
Organization
Cited Papers
Interventricular Electrical Delay Is Predictive of Response to Cardiac Resynchronization Therapy
PREAI
ShareSaveShareSaveCognition Based Seamless Transmissions by Using Underlay-Overlay Switching Method in Future Wireless Communication System.png)
2007 2nd International Conference on Cognitive Radio Oriented Wireless Networks and Communications
2007 2nd International Conference on Cognitive Radio Oriented Wireless Networks and CommunicationsIF0
PREAI
ShareSaveMultimodal Data Fusion: An Overview of Methods, Challenges, and ProspectsPROCEEDINGS OF THE IEEE
OAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAIShareSaveTiny noise, big mistakes: adversarial perturbations induce errors in brain-computer interface spellersNATIONAL SCIENCE REVIEWOAAI
NATIONAL SCIENCE REVIEWIF17.1
OAAIShareSaveShareSave
View more