Results 251 to 260 of about 804,777 (293)

Byzantine robust federated learning for heterogeneous brain MRI using multisignal gradient fingerprinting and adaptive trust aggregation. [PDF]

Sci Rep
Karami M, Kebriaei H, Ghassemi F, Azadegan H.   +3 more
europepmc   +1 more source

Cyborg-swarm cooperation and game via affective-based brain-machine interface. [PDF]

Natl Sci Rev
Chen Z, Zhang L, Chen G, Liu H, Wang Z, Zhao X, Guo S, Zhao T, Sun M, Liang W, Qin L, Zhang M, Liu L, Wang W.   +13 more
europepmc   +1 more source

Adversarial anchor-guided feature refinement for adversarial defense

Image and Vision Computing, 2023
Adversarial training (AT), which is known as a robust training method for defending against adversarial examples, usually loses the performance of models for clean examples due to the feature distribution discrepancy between clean and adversarial.
Hakmin Lee, Yong Man Ro
openaire   +3 more sources

Adversarial Attack and Defense: A Survey

Electronics (Switzerland), 2022
In recent years, artificial intelligence technology represented by deep learning has achieved remarkable results in image recognition, semantic analysis, natural language processing and other fields.
Erlu He, Yangyang Zhao
exaly   +2 more sources

Some of the next articles are maybe not open access.

Related searches:

Adversarial Attacks and Defenses on Graphs

ACM SIGKDD Explorations Newsletter, 2021
Deep neural networks (DNNs) have achieved significant performance in various tasks. However, recent studies have shown that DNNs can be easily fooled by small perturbation on the input, called adversarial attacks.
Wei Jin 0009, Yaxin Li 0001, Han Xu 0002, Yiqi Wang 0001, Shuiwang Ji, Charu Aggarwal 0001, Jiliang Tang   +6 more
openaire   +1 more source

Sinkhorn Adversarial Attack and Defense

IEEE Transactions on Image Processing, 2022
Adversarial attacks have been extensively investigated in the recent past. Quite interestingly, a majority of these attacks primarily work in the lp space. In this work, we propose a novel approach for generating adversarial samples using Wasserstein distance.
openaire   +2 more sources

Perturbation Inactivation Based Adversarial Defense for Face Recognition

IEEE Transactions on Information Forensics and Security, 2022
Deep learning-based face recognition models are vulnerable to adversarial attacks. To curb these attacks, most defense methods aim to improve the robustness of recognition models against adversarial perturbations.
Min Ren, Yunlong Wang, Zhenan Sun
exaly   +1 more source

Robust Defense Against Adversarial Attacks with Defensive Preprocessing and Adversarial Training

2025 IEEE International Conference on Consumer Electronics (ICCE)
Deep learning technologies have rapidly advanced, but concerns about their security and vulnerability to threats have emerged. Adversarial attacks, using carefully crafted perturbations, exploit these weaknesses, posing serious risks. This study introduces an integrated defensive preprocessing and adversarial training pipeline as a robust defense ...
Chih-Yang Lin, Bing-Hua Lai, Hui-Fuang Ng, Wei-Yang Lin, Ming-Ching Chang   +4 more
openaire   +1 more source