Presentation | 2020-03-11 Fairness Causes Vulnerability to Adversarial Attacks Koki Wataoka, Takashi Matsubara, Kuniaki Uehara, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | When using machine learning models in society, it is essential to be ensure classifiers are fair to race and gender. In recent yeas, many methods have been proposed to make classifiers fair. However, the security of fair classifiers has been rarely discussed. In the field of machine learning, there is an attack method called adversarial attacks that reduce the accuracy of classifiers. In this paper, fair classifiers are vulnerable to adversarial attacks. Our experiment has shown that fair classifiers are less robust against adversarial attacks than usual classifiers and hence worse classification accuracy and part of fairness performance. Key words Fairness, Adversarial Attacks, Adversarial Training |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Fairness / Adversarial Attacks / Adversarial Training |
Paper # | IBISML2019-48 |
Date of Issue | 2020-03-03 (IBISML) |
Conference Information | |
Committee | IBISML |
---|---|
Conference Date | 2020/3/10(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Kyoto University |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Machine learning, etc. |
Chair | Hisashi Kashima(Kyoto Univ.) |
Vice Chair | Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
Secretary | Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST) |
Assistant | Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.) |
Paper Information | |
Registration To | Technical Committee on Infomation-Based Induction Sciences and Machine Learning |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Fairness Causes Vulnerability to Adversarial Attacks |
Sub Title (in English) | |
Keyword(1) | Fairness |
Keyword(2) | Adversarial Attacks |
Keyword(3) | Adversarial Training |
1st Author's Name | Koki Wataoka |
1st Author's Affiliation | Kobe University(Kobe Univ.) |
2nd Author's Name | Takashi Matsubara |
2nd Author's Affiliation | Kobe University(Kobe Univ.) |
3rd Author's Name | Kuniaki Uehara |
3rd Author's Affiliation | Kobe University(Kobe Univ.) |
Date | 2020-03-11 |
Paper # | IBISML2019-48 |
Volume (vol) | vol.119 |
Number (no) | IBISML-476 |
Page | pp.pp.101-105(IBISML), |
#Pages | 5 |
Date of Issue | 2020-03-03 (IBISML) |