Generating Adversarial Examples by Adversarial Networks for Semi-supervised Learning

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with host publication)peer-review

View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationWeb Information Systems Engineering – WISE 2019 - 20th International Conference, Proceedings
EditorsReynold Cheng, Nikos Mamoulis, Yizhou Sun
PublisherSpringer
Pages115-129
ISBN (Electronic)9783030342234
ISBN (Print)9783030342227
Publication statusPublished - Jan 2020

Publication series

NameLecture Notes in Computer Science
Volume11881
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Title20th International Conference on Web Information Systems Engineering (WISE 2019)
PlaceChina
CityHong Kong
Period19 - 21 January 2020

Abstract

Semi-Supervised Learning (SSL) has exhibited strong effectiveness in boosting the performance of classification models with the aid of a large amount of unlabeled data. Recently, regularizing the classifier with the help of adversarial examples has proven effective for semi-supervised learning. Existing methods hypothesize that the adversarial examples are based on the pixel-wise perturbation of the original samples. However, other types of adversarial examples (e.g., with spatial transformation) should also be useful for improving the robustness of the classifier. In this paper, we propose a new generalized framework based on adversarial networks, which is able to generate various types of adversarial examples. Our model consists of two modules which are trained in an adversarial process: a generator mapping the original samples to adversarial examples which can fool the classifier, and a classifier that tries to classify the original samples and the adversarial examples consistently. We evaluate our model on several datasets, and the experimental results show that our model outperforms the state-of-the-art methods for semi-supervised learning. The experiments also demonstrate that our model can generate adversarial examples with various types of perturbation such as local spatial transformation, color transformation, and pixel-wise perturbation. Moreover, our model is also applicable to supervised learning, performing as a regularization term to improve the generalization performance of the classifier.

Research Area(s)

  • Adversarial examples, Adversarial networks, Semi-supervised learning

Citation Format(s)

Generating Adversarial Examples by Adversarial Networks for Semi-supervised Learning. / Ma, Yun; Mao, Xudong; Chen, Yangbin et al.
Web Information Systems Engineering – WISE 2019 - 20th International Conference, Proceedings. ed. / Reynold Cheng; Nikos Mamoulis; Yizhou Sun. Springer, 2020. p. 115-129 (Lecture Notes in Computer Science; Vol. 11881).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with host publication)peer-review