Work

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

Year: 2026

Type: preprint

Abstract: 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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2608.04680

Authors: Goyal, Anadi, Chattopadhyay, Nandish, Karfa, Chandan, Chattopadhyay, Anupam, Rattanavipanon, Norrathep

Institutions: Indian Institute of Technology Guwahati, Nanyang Technological University, Prince of Songkla University

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7196969320

Cites:

Cited by:

Related to: