The paper investigates federated adversarial training (AT) for vision transformers, a topic not previously explored in federated learning (FL). It evaluates various transformer architectures and aggregation strategies, and introduces FedWAvg, an extension of FedAvg that weights client updates based on similarity of their last-layer representations. Experiments demonstrate that FedWAvg yields higher robust accuracy than existing aggregation methods in non‑IID settings.
arXiv:2606. 28416v1 Announce Type: cross Abstract: Deep neural networks (DNNs) have shown outstanding performance in visual recognition tasks within vision sensor networks; however, they are still vulnerable to adversarial manipulations and imperceptible perturbations that can lead to erroneous predictions.
arXiv:2607. 09480v1 Announce Type: cross Abstract: The human visual system (HVS) employs foveated sampling and eye movements to achieve efficient perception, conserving both metabolic energy and computational resources.
arXiv:2606. 02267v1 Announce Type: new Abstract: The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment.
arXiv:2607. 04145v1 Announce Type: new Abstract: Adversarial attacks guide and provide additional training and test data for both adversarial training and adversarial robustness validation, and expose the 'piecewise linearity' of deep learning based models.
arXiv:2409. 17754v2 Announce Type: replace-cross Abstract: Federated Learning (FL) emerges as a distributed machine learning approach that addresses privacy concerns by training AI models locally on devices.
arXiv:2511. 17688v2 Announce Type: replace-cross Abstract: Input transformation-based attacks improve adversarial transferability by aggregating gradients over transformed inputs.
arXiv:2609.07403v1 Announce Type: cross Abstract: Privacy-sensitive surveillance systems could benefit from large vision-language models (VLMs), but such models typically require centralized access t...
arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.
arXiv:2608. 07750v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) have found successful deployment in numerous vision perception systems.
Vision Transformers (ViTs) increasingly rely on input-adaptive inference, such as token pruning and early halting, to meet energy and latency budgets. This survey examines a recent class of adversarial efficiency degradation attacks that target these mechanisms to increase computation without necessarily degrading accuracy.
FSPGD introduces a feature-space black-box attack for semantic segmentation that targets intermediate representations rather than just output logits. The method uses a dual loss: an external loss to disrupt cross-model feature alignment and an internal loss to reduce consistency among same-class instances. Experiments on Pascal VOC 2012 and Cityscapes show that FSPGD outperforms existing logit-level and segmentation-specific attacks across CNN and Transformer backbones, and its adversarial examples improve robustness when used for training.
arXiv:2606. 01746v1 Announce Type: cross Abstract: Modern neural networks are highly susceptible to adversarial perturbations.