English(EN) MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs

MOAT防御流水线保护Vision Transformer免受效率下降攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-06 04:00

研究人员推出了一种新颖的防御流水线MOAT，旨在保护Vision Transformer（ViT）免受会降低其效率的对抗性攻击。MOAT采用一系列输入变换，使其具有模型无关性，并与用于降低计算成本的现有令牌修剪技术兼容。实验表明，MOAT有效地将攻击下的GFLOPs下降限制在原始模型性能的3.4%以内。 AI

影响增强了资源受限环境中Vision Transformer的鲁棒性，使其在对抗性操纵下更加可靠。

排序理由该集群包含一篇学术论文，详细介绍了一种提高AI模型安全性方面的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了一种提高AI模型安全性方面的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 60 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Anadi Goyal, Nandish Chattopadhyay, Chandan Karfa, Anupam Chattopadhyay, Norrathep Rattanavipanon · 2026-08-06 04:00

MOAT：模型无关的随机变换，用于防止ViT上的效率下降攻击

arXiv:2608.04680v1 Announce Type: cross 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 t…

本文如何被排名

报道来源 [1]

MOAT：模型无关的随机变换，用于防止ViT上的效率下降攻击

相关实体

相关话题