通过分离相位与幅度信息，提升模型对抗攻击的鲁棒性。
Improving Adversarial Robustness via Phase and Amplitude-aware Prompting
- 分离构建相位与幅度提示，精准聚焦语义特征
- 在多个数据集上实现更高对抗鲁棒性
- 适合需要高效防御的视觉任务场景
深度神经网络易受对抗扰动影响。由于高效性，基于提示的防御方法受到越来越多关注。然而，现有提示防御多采用混合提示模式，对与物体语义密切相关的关键模式关注不足。研究表明，相位和幅度谱与特定语义模式密切相关，对模型鲁棒性至关重要。为此，本文提出相位与幅度感知提示（PAP）防御方法。具体而言，为每个类别构建相位级和幅度级提示，并在训练中根据模型在这些提示下的鲁棒表现调整提示权重。测试时，根据图像的预测标签选择对应提示，生成提示图像后输入模型获得最终预测。实验结果验证了该方法的有效性。
原文摘要 · Abstract (English)
Deep neural networks are found to be vulnerable to adversarial perturbations. The prompt-based defense has been increasingly studied due to its high efficiency. However, existing prompt-based defenses mainly exploited mixed prompt patterns, where critical patterns closely related to object semantics lack sufficient focus. The phase and amplitude spectra have been proven to be highly related to specific semantic patterns and crucial for robustness. To this end, in this paper, we propose a Phase and Amplitude-aware Prompting (PAP) defense. Specifically, we construct phase-level and amplitude-level prompts for each class, and adjust weights for prompting according to the model's robust performance under these prompts during training. During testing, we select prompts for each image using its predicted label to obtain the prompted image, which is inputted to the model to get the final prediction. Experimental results demonstrate the effectiveness of our method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。