---
title: "卷积扰动的认证训练：为视觉模型提供形式化安全保证"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.18195v1"
permalink: "https://feed.astralor.com/items/itm_b25335857a25c21136eb5f08"
published: "2026-07-20T17:36:05.000Z"
score: 81
channel: "ai"
tags: ["CIFAR10","卷积扰动","可证明鲁棒性","认证训练","运动模糊"]
---

# 卷积扰动的认证训练：为视觉模型提供形式化安全保证

## AI 点评

> 这篇论文将认证训练从Lp范数扰动拓展到卷积扰动，是鲁棒性研究的一个重要进步。对于正在部署视觉模型到物理世界的团队（如自动驾驶、机器人），这个工作直接告诉你如何获得形式化安全保证，而不仅仅是凭经验感觉。虽然实验只在CIFAR10上做，但方法本身具有通用性，值得跟踪后续在ImageNet等更大规模上的表现。

## 速览

视觉模型对运行时抖动引起的运动模糊等卷积扰动高度敏感，可能导致关键应用失败。现有数据增强或对抗训练仅提升经验鲁棒性，缺乏形式化安全保证。本文提出一种新颖的认证训练方法，通过高效编码卷积扰动来训练可证明鲁棒的模型。在CIFAR10上，该方法在合理强度运动模糊下实现超过80%的鲁棒准确率，同时保持相当的常规准确率，显著优于对抗训练。

## 关键点

- 提出针对卷积扰动（如运动模糊）的认证训练方法，首次将可证明鲁棒性扩展至此类扰动。
- 通过高效编码卷积扰动，实现训练时的可证边界计算，不显著增加计算成本。
- 在CIFAR10数据集上，该方法在合理强度运动模糊下鲁棒准确率超过80%，且标准准确率与普通训练相近。
- 与对抗训练相比，认证训练在鲁棒性上大幅领先，并能识别对抗训练未能覆盖的隐藏脆弱点。

## 全文

Vision models have been found to be susceptible to perturbations such as motion blur induced at runtime by a shaking camera. This impedes their deployment in critical applications since phenomena such as slightly blurred vision might lead to failures, for example an object detector missing objects. While methods such as data augmentation or Adversarial Training can improve empirical robustness, they lack formal safety guarantees, making it difficult to identify and mitigate hidden vulnerabilities. We introduce a novel Certified Training approach that leverages an efficient encoding of convolutional perturbations to train provably robust models. Our method significantly outperforms Adversarial Training, achieving, for example, over 80% robust accuracy against motion blur of reasonable intensity on CIFAR10 while maintaining comparable standard accuracy.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_b25335857a25c21136eb5f08