Adversarial robustness is a key concept in measuring the ability of neural networks to defend against adversarial attacks during the inference phase. Recent studies have shown that despite the success of improving adversarial robustness against a single type of attack using robust training techniques, models are still vulnerable to diversified $\ell_p$ attacks. To achieve diversified $\ell_p$ robustness, we propose a novel robust mode connectivity (RMC)-oriented adversarial defense that contains two population-based learning phases. The first phase, RMC, is able to search the model parameter space between two pre-trained models and find a path containing points with high robustness against diversified $\ell_p$ attacks. In light of the effectiveness of RMC, we develop a second phase, RMC-based optimization, with RMC serving as the basic unit for further enhancement of neural network diversified $\ell_p$ robustness. To increase computational efficiency, we incorporate learning with a self-robust mode connectivity (SRMC) module that enables the fast proliferation of the population used for endpoints of RMC. Furthermore, we draw parallels between SRMC and the human immune system. Experimental results on various datasets and model architectures demonstrate that the proposed defense methods can achieve high diversified $\ell_p$ robustness against $\ell_\infty$, $\ell_2$, $\ell_1$, and hybrid attacks. Codes are available at \url{https://github.com/wangren09/MCGR}.

翻译：对抗鲁棒性是衡量神经网络在推理阶段抵御对抗攻击能力的关键概念。近期研究表明，尽管使用鲁棒训练技术能成功提升模型对单一类型攻击的鲁棒性，但模型在面对多样化$\ell_p$攻击时仍然脆弱。为实现多样化$\ell_p$鲁棒性，我们提出了一种新颖的基于鲁棒模式连通性（RMC）的对抗防御方法，该方法包含两个基于种群的训练阶段。第一阶段（RMC）能够在两个预训练模型之间搜索参数空间，并找到一条包含高鲁棒性点的路径以抵御多样化$\ell_p$攻击。鉴于RMC的有效性，我们开发了第二阶段（RMC优化），以RMC为基本单元进一步提升神经网络的多样化$\ell_p$鲁棒性。为提高计算效率，我们引入了带自鲁棒模式连通性（SRMC）模块的学习机制，该模块能够快速扩充RMC端点的种群规模。此外，我们将SRMC与人类免疫系统进行类比。在多种数据集和模型架构上的实验结果表明，所提出的防御方法能够针对$\ell_\infty$、$\ell_2$、$\ell_1$及混合攻击实现高水平的多样化$\ell_p$鲁棒性。相关代码已开源至\url{https://github.com/wangren09/MCGR}。