Securing Vision Transformers Against Adversarial Attacks via Input Purification in Trusted Execution Environments
- 1 October 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 18 (5) , 456-459
Abstract
No abstract availableFunding Information
- Ministry of Science, Research and the Arts of Baden-Württemberg (MWK) through the Karlsruhe Chipdesign House (KCH) Project
This publication has 7 references indexed in Scilit:
- Robust Evaluation of Diffusion-Based Adversarial Purification2023
- Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environments2023
- On the Robustness of Vision Transformers to Adversarial Examples2021
- An Efficient Preprocessing-Based Approach to Mitigate Advanced Adversarial AttacksIEEE Transactions on Computers, 2021
- Big Transfer (BiT): General Visual Representation Learning2020
- Barrage of Random Transforms for Adversarially Robust Defense2019
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image DenoisingIEEE Transactions on Image Processing, 2017