MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs

Computer Science > Cryptography and Security [Submitted on 5 Aug 2026] MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs Anadi Goyal, Nandish Chattopadhyay, Chandan Karfa, Anupam Chattopadhyay, Norrathep Rattanavipanon To adopt the Vision Transformers (ViTs) in resource-constrained environment, token pruning is widely used to reduce computational cost without impacting accuracy. However, adversaries have developed targeted attacks against said token pruning techniques to undermine such attempts to make ViTs efficient. In this paper, we propose MOAT, a model-agnostic pre-processing defense pipeline that applies a combination of input transformations to protect efficient ViT implementations against adversarial efficiency attacks. MOAT operates directly on the input without requiring modifications to the model architecture or token pruning mechanism. Experimental results demonstrate that, across all evaluated ViT models, MOAT limits GFLOPs degradation under adversarial attacks to within 3.4% of the original unattacked model. Comments: This paper has been accepted for publication at IEEE ISVLSI 2026 Subjects: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.04680 [cs.CR]   (or arXiv:2608.04680v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2608.04680 Focus to learn more Submission history From: Nandish Chattopadhyay [view email] [v1] Wed, 5 Aug 2026 10:47:58 UTC (2,603 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-08 Change to browse by: cs cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)