MOAT defense pipeline protects Vision Transformers from efficiency degradation attacks

Researchers have introduced MOAT, a novel defense pipeline designed to protect Vision Transformers (ViTs) from adversarial attacks that degrade their efficiency. MOAT employs a series of input transformations, making it model-agnostic and compatible with existing token pruning techniques used to reduce computational costs. Experiments show that MOAT effectively limits the degradation of GFLOPs under attack to within 3.4% of the original model's performance. AI

IMPACT Enhances the robustness of Vision Transformers in resource-constrained environments, making them more reliable against adversarial manipulation.

RANK_REASON The cluster contains an academic paper detailing a new method for improving AI model security. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• arXiv
• DagsHub
• Hugging Face
• MOAT
• Nandish Chattopadhyay
• Vision Transformers
• Vits

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →