通过基于分数的优化增强对抗鲁棒性
Enhancing Adversarial Robustness via Score-Based Optimization
AI总结：
本文提出 ScoreOpt 对抗防御方案，利用基于分数的先验在测试时优化对抗样本，在 CIFAR10、CIFAR100 和 ImageNet 上同时提升了鲁棒性与推理速度。
摘要：
对抗攻击有可能通过引入微小扰动来误导深度神经网络分类器。开发能够减轻这些攻击影响的算法对于确保人工智能的安全使用至关重要。最近的研究表明，基于分数的扩散模型在对抗防御中是有效的。然而，现有的基于扩散的防御依赖于对扩散模型的反向随机微分方程进行顺序模拟，这计算效率低下且产生次优结果。在本文中，我们提出了一种新颖的对抗防御方案，名为 ScoreOpt，它在测试时沿基于分数的先验引导的方向，将对抗样本优化回原始干净数据。我们在多个数据集上进行了全面实验，包括 CIFAR10、CIFAR100 和 ImageNet。我们的实验结果表明，我们的方法在鲁棒性性能和推理速度方面均优于现有的对抗防御方法。
英文摘要：
Adversarial attacks have the potential to mislead deep neural network classifiers by introducing slight perturbations. Developing algorithms that can mitigate the effects of these attacks is crucial for ensuring the safe use of artificial intelligence. Recent studies have suggested that score-based diffusion models are effective in adversarial defenses. However, existing diffusion-based defenses rely on the sequential simulation of the reversed stochastic differential equations of diffusion models, which are computationally inefficient and yield suboptimal results. In this paper, we introduce a novel adversarial defense scheme named ScoreOpt, which optimizes adversarial samples at test-time, towards original clean data in the direction guided by score-based priors. We conduct comprehensive experiments on multiple datasets, including CIFAR10, CIFAR100 and ImageNet. Our experimental results demonstrate that our approach outperforms existing adversarial defenses in terms of both robustness performance and inference speed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
