Improving the Robustness of Deep Neural Networks via Adversarial Training with Triplet Loss
원문 초록
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 (AT$^2$L), 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 AT$^2$L, 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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Globally Correlation-Aware Hard Negative Generation
Radar Pulse Deinterleaving with Transformer Based Deep Metric Learning
Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learning
Anomaly Triplet-Net: Progress Recognition Model Using Deep Metric Learning Considering Occlusion for Manual Assembly Work
Why and How: Knowledge-Guided Learning for Cross-Spectral Image Patch Matching
Attributes Shape the Embedding Space of Face Recognition Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.