arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.14795cs.LGcs.CRcs.CV
收藏

Ensemble-in-One:随机门控网络中增强对抗鲁棒性的学习包围

Ensemble-in-One: Learning Ensemble within Random Gated Networks for Enhanced Adversarial Robustness

Tsinghua University(清华大学)

Yi Cai, Xuefei Ning, Huazhong Yang, Yu Wang

摘要:

对抗攻击给现代深度学习系统带来了很高的安全风险。对抗性训练可以通过抑制非鲁棒性特征来显著增强神经网络模型的鲁棒性。然而,这些模型在干净的数据上往往会遭受显著的准确性损失。包围训练方法已经成为防御对抗攻击的有前途的解决方案,它通过使子模型之间的漏洞多样化,同时保持与标准训练相当的准确性。然而,现有的集成方法的可扩展性差,由于快速增加的复杂性时,包括更多的子模型在集成。此外,在现实世界的应用中,由于紧张的硬件资源预算和延迟要求,很难部署具有多个子模型的集成。在这项工作中,我们提出了集成在一个(EIO),一个简单而有效的方法来训练一个集成在一个随机门控网络(RGN)。EIO通过用多路径随机门控块(RGBs)替换参数化层来构建RGN,从而增强了原始模型。通过使RGN内的众多路径的脆弱性多样化,可以实现更好的鲁棒性。由于EIO网络中的路径随着网络深度呈指数级增长,因此它提供了高可扩展性。我们的实验表明,EIO始终优于以前的集成训练方法,甚至更少的计算开销。

英文摘要:

Adversarial attacks have rendered high security risks on modern deep learning systems. Adversarial training can significantly enhance the robustness of neural network models by suppressing the non-robust features. However, the models often suffer from significant accuracy loss on clean data. Ensemble training methods have emerged as promising solutions for defending against adversarial attacks by diversifying the vulnerabilities among the sub-models, simultaneously maintaining comparable accuracy as standard training. However, existing ensemble methods are with poor scalability, owing to the rapid complexity increase when including more sub-models in the ensemble. Moreover, in real-world applications, it is difficult to deploy an ensemble with multiple sub-models, owing to the tight hardware resource budget and latency requirement. In this work, we propose ensemble-in-one (EIO), a simple but efficient way to train an ensemble within one random gated network (RGN). EIO augments the original model by replacing the parameterized layers with multi-path random gated blocks (RGBs) to construct a RGN. By diversifying the vulnerability of the numerous paths within the RGN, better robustness can be achieved. It provides high scalability because the paths within an EIO network exponentially increase with the network depth. Our experiments demonstrate that EIO consistently outperforms previous ensemble training methods with even less computational overhead.

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。

↑