arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.08233cs.CV
收藏

标签平滑和对抗鲁棒性

Label Smoothing and Adversarial Robustness

Shanghai Jiao Tong University(上海交通大学);BNU-UIC Institute of Artificial Intelligence and Future Networks(北师大-浸大人工智能与未来网络研究院);Beijing Normal University (BNU Zhuhai)(北京师范大学(珠海));BNU-HKBU United International College(北京师范大学-香港浸会大学联合国际学院)

Chaohao Fu, Hongbin Chen, Na Ruan, Weijia Jia

摘要:

近年来的研究表明,当前的对抗攻击方法存在缺陷,在遇到一些故意设计的防御时容易失败。有时,即使是对模型细节的轻微修改也会使攻击无效。我们发现,标签平滑的训练模型可以很容易地达到打击精度在大多数基于梯度的攻击。例如,在CIFAR-10上使用标签平滑训练的WideResNet模型在PGD攻击下的鲁棒准确率最高达到75%。为了理解微妙的鲁棒性背后的原因,我们研究了标签平滑和对抗鲁棒性之间的关系。通过对标签平滑训练的网络的特性进行理论分析,并通过实验验证其在各种攻击下的性能。我们证明了标签平滑产生的鲁棒性是不完整的,基于这样一个事实,即它的防御效果是不稳定的,它不能防御来自自然训练模型的攻击。我们的研究启发了研究界重新思考如何适当地评估模型的鲁棒性。

英文摘要:

Recent studies indicate that current adversarial attack methods are flawed and easy to fail when encountering some deliberately designed defense. Sometimes even a slight modification in the model details will invalidate the attack. We find that training model with label smoothing can easily achieve striking accuracy under most gradient-based attacks. For instance, the robust accuracy of a WideResNet model trained with label smoothing on CIFAR-10 achieves 75% at most under PGD attack. To understand the reason underlying the subtle robustness, we investigate the relationship between label smoothing and adversarial robustness. Through theoretical analysis about the characteristics of the network trained with label smoothing and experiment verification of its performance under various attacks. We demonstrate that the robustness produced by label smoothing is incomplete based on the fact that its defense effect is volatile, and it cannot defend attacks transferred from a naturally trained model. Our study enlightens the research community to rethink how to evaluate the model's robustness appropriately.

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。

↑