卷积扰动的认证训练
Certified Training for Convolutional Perturbations
浏览论文内容
中文总结 AI 辅助
研究视觉模型受扰动问题，提出利用卷积扰动编码的认证训练方法，显著优于对抗训练，在CIFAR10上对运动模糊有超80%鲁棒准确率，且标准准确率相当。
中文摘要 AI 辅助
视觉模型易受运行时相机抖动引起的运动模糊等扰动影响，这阻碍了它们在关键应用中的部署。数据增强或对抗训练等方法缺乏形式安全保证。我们引入一种新颖的认证训练方法，利用卷积扰动的高效编码来训练可证明鲁棒的模型。该方法显著优于对抗训练，在CIFAR10上对合理强度运动模糊的鲁棒准确率超过80%，同时保持相当的标准准确率。
英文摘要
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.
发表机构
- Safe Intelligence（安全智能）
- Imperial College London（伦敦帝国理工学院）
机构由 AI 辅助整理，请以论文原文为准。
