Improving the Robustness of Deep Neural Networks via Adversarial Training with Triplet Loss

By Pengcheng Li, Jinfeng Yi, Bowen Zhou, Lijun Zhang. 2019

39 citations recorded by the source corpus.

Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial examples. In this paper, we improve the robustness of DNNs by utilizing techniques of Distance Metric Learning. Specifically, we incorporate Triplet Loss, one of the most popular Distance Metric Learning methods, into the framework of adversarial training. Our proposed algorithm, Adversarial Training with Triplet Loss (AT2L), substitutes the adversarial example against the current model for the anchor of triplet loss to effectively smooth the classification boundary. Furthermore, we propose an ensemble version of AT2L, which aggregates different attack methods and model structures for better defense effects. Our empirical studies verify that the proposed approach can significantly improve the robustness of DNNs without sacrificing accuracy. Finally, we demonstrate that our specially designed triplet loss can also be used as a regularization term to enhance other defense methods.

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tianyu Pang
2. Hang Su
3. Jun Zhu
4. Yinpeng Dong
5. Xiao Yang
6. Vamsi Krishna Ithapu
7. Alan L. Yuille
8. Matthias Hein

In Molecular Biology

1. Jun Zhu
2. Tianyu Pang
3. Hang Su
4. Xiao Yang
5. Yinpeng Dong

Citations in the corpus

• Bag of Tricks for Adversarial Training (2020, background): “…the mechanisms inspired from other domains, including ensemble learning (Tramèr et al., 2018; Pang et al., 2019), metric learning (Mao et al., 2019; Li et al., 2019; Pang et al., 2020c), generative modeling (Jiang et al., 2018; Pang et al., 2018b; Wang & Yu, 2019; Deng et al., 2020),…”