arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.03110cs.CVcs.AI
收藏

RobArch:设计鲁棒的体系结构以抵御对抗攻击

RobArch: Designing Robust Architectures against Adversarial Attacks

Georgia Institute of Technology(佐治亚理工学院);Intel Corporation(英特尔公司)

ShengYun Peng, Weilin Xu, Cory Cornelius, Kevin Li, Rahul Duggal, Duen Horng Chau, Jason Martin

摘要:

对抗性训练是提高深度神经网络(DNN)鲁棒性的最有效方法。然而,与优化对抗训练过程的大量研究相比,很少有关于架构组件如何影响鲁棒性的研究,它们很少限制模型容量。因此,目前还不清楚鲁棒性究竟来自哪里。在这项工作中,我们提出了第一个大规模的系统研究DNN架构组件的鲁棒性在固定的参数预算。通过我们的调查,我们提炼出18个可操作的健壮网络设计指南,使模型开发人员能够获得深刻的见解。我们通过引入新的鲁棒架构(RobArch)模型来证明这些准则的有效性,该模型实例化了这些准则,以构建一系列针对强对抗攻击的跨参数能力的最佳性能模型。RobArch在RobustBench ImageNet排行榜上达到了最先进的AutoAttack精度。代码可在$\href{https://github.com/ShengYun-Peng/RobArch}{\text{this url}}$上获得。

英文摘要:

Adversarial Training is the most effective approach for improving the robustness of Deep Neural Networks (DNNs). However, compared to the large body of research in optimizing the adversarial training process, there are few investigations into how architecture components affect robustness, and they rarely constrain model capacity. Thus, it is unclear where robustness precisely comes from. In this work, we present the first large-scale systematic study on the robustness of DNN architecture components under fixed parameter budgets. Through our investigation, we distill 18 actionable robust network design guidelines that empower model developers to gain deep insights. We demonstrate these guidelines' effectiveness by introducing the novel Robust Architecture (RobArch) model that instantiates the guidelines to build a family of top-performing models across parameter capacities against strong adversarial attacks. RobArch achieves the new state-of-the-art AutoAttack accuracy on the RobustBench ImageNet leaderboard. The code is available at $\href{https://github.com/ShengYun-Peng/RobArch}{\text{this url}}$.

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。

↑