若求稳健，须警惕初始化
If You Want to Be Robust, Be Wary of Initialization
AI总结：
本研究揭示权重初始化及训练轮数直接影响图神经网络对抗鲁棒性，提出理论框架并实验验证，表明恰当初始化可提升高达50%的鲁棒性。
摘要：
图神经网络（GNNs）在各类图相关任务中展现了卓越的性能，然而其对抗性扰动的脆弱性仍令人担忧。尽管现有的防御策略主要集中于预处理技术和自适应消息传递方案，本研究探索了一个尚未充分研究的维度：权重初始化及相关超参数（如训练轮数）对模型鲁棒性的影响。我们提出了一个理论框架，将初始化策略与网络对对抗性扰动的抵抗力联系起来。我们的分析揭示了初始权重、训练轮数与模型脆弱性之间的直接关系，为超越传统防御机制的对抗鲁棒性提供了新见解。虽然我们的主要关注点是GNN，但我们扩展了理论框架，为深度神经网络（DNNs）提供了通用的上界。涵盖多种模型和真实世界数据集、并经受各种对抗性攻击的广泛实验验证了我们的发现。我们证明，选择合适的初始化不仅能确保在干净数据集上的性能，还能增强模型对对抗性扰动的鲁棒性，与替代初始化方法相比，观察到的差距高达50%。
英文摘要：
Graph Neural Networks (GNNs) have demonstrated remarkable performance across a spectrum of graph-related tasks, however concerns persist regarding their vulnerability to adversarial perturbations. While prevailing defense strategies focus primarily on pre-processing techniques and adaptive message-passing schemes, this study delves into an under-explored dimension: the impact of weight initialization and associated hyper-parameters, such as training epochs, on a model's robustness. We introduce a theoretical framework bridging the connection between initialization strategies and a network's resilience to adversarial perturbations. Our analysis reveals a direct relationship between initial weights, number of training epochs and the model's vulnerability, offering new insights into adversarial robustness beyond conventional defense mechanisms. While our primary focus is on GNNs, we extend our theoretical framework, providing a general upper-bound applicable to Deep Neural Networks. Extensive experiments, spanning diverse models and real-world datasets subjected to various adversarial attacks, validate our findings. We illustrate that selecting appropriate initialization not only ensures performance on clean datasets but also enhances model robustness against adversarial perturbations, with observed gaps of up to 50\% compared to alternative initialization approaches.
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。
