CausalDiff：基于扩散模型的因果启发的解缠结对抗防御方法
CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
AI总结：
提出CausalDiff，基于扩散模型解缠结因果因素，仅依赖标签因果因素预测，在多种未见攻击下显著提升鲁棒性。
摘要：
尽管人们不断努力保护神经分类器免受对抗性攻击，但它们仍然脆弱，尤其是面对未见过的攻击。相比之下，人类很难被微妙的操纵所欺骗，因为我们只基于本质因素做出判断。受此观察启发，我们尝试用本质的标签因果因素来建模标签生成，并引入标签非因果因素来辅助数据生成。对于对抗性样本，我们旨在将扰动区分为非因果因素，并仅基于标签因果因素进行预测。具体而言，我们提出了一种因果扩散模型（CausalDiff），该模型将扩散模型适配于条件数据生成，并通过学习一种新颖的因果信息瓶颈目标来解缠结这两类因果因素。实验上，CausalDiff在各种未见攻击上显著优于最先进的防御方法，在CIFAR-10上实现了86.39%（+4.01%）的平均鲁棒性，在CIFAR-100上为56.25%（+3.13%），在GTSRB（德国交通标志识别基准）上为82.62%（+4.93%）。代码可在https://github.com/CAS-AISafetyBasicResearchGroup/CausalDiff获取。
英文摘要：
Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark). The code is available at https://github.com/CAS-AISafetyBasicResearchGroup/CausalDiff.
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。
