Presentation 2018-07-02
Effect of Flactuation of Training Data on Prediction Performance
Sachio Hirokawa, Koji Okamura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) By applying machine learning to the case of spam, a spam identification model can be created. On the other hand, the attacker can attack different patterns by estimating the model of the defender from the spam filter case. In this research, we thought that the defending side could slightly change the model, thereby reducing the prediction performance of the attacking side. As a preliminary experiment, we evaluated how much the discrimination performance would be decreased when one positive instance in the trainning data were changed to negative.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Adversarial Machine Learning / Flactuation of Training Data / Prediction Performance
Paper # AI2018-3
Date of Issue 2018-06-25 (AI)

Conference Information
Committee AI
Conference Date 2018/7/2(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tsunenori Mine(Kyushu Univ.)
Vice Chair Daisuke Katagami(Tokyo Polytechnic Univ.) / Naoki Fukuta(Shizuoka Univ.)
Secretary Daisuke Katagami(Ritsumeikan Univ.) / Naoki Fukuta(Univ. of Electro-Comm.)
Assistant Yuko Sakurai(AIST)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Effect of Flactuation of Training Data on Prediction Performance
Sub Title (in English)
Keyword(1) Adversarial Machine Learning
Keyword(2) Flactuation of Training Data
Keyword(3) Prediction Performance
1st Author's Name Sachio Hirokawa
1st Author's Affiliation Kyushu University(Kyushu Univ.)
2nd Author's Name Koji Okamura
2nd Author's Affiliation Kyushu University(Kyushu Univ.)
Date 2018-07-02
Paper # AI2018-3
Volume (vol) vol.118
Number (no) AI-116
Page pp.pp.11-14(AI),
#Pages 4
Date of Issue 2018-06-25 (AI)