Presentation | 2022-06-27 Evaluating and Enhancing Reliabilities of AI-Powered Tools Jingfeng Zhang, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | When we deploy models trained by standard training (ST), they work well on natural test data. However, those models cannot handle adversarial test data (also known as adversarial examples) that are algorithmically generated by adversarial attacks. An adversarial attack is an algorithm which applies specially designed tiny perturbations on natural data to transform them into adversarial data, in order to mislead a trained model and let it give wrong predictions. Adversarial training (AT) aims at improving the robust accuracy of trained models against adversarial attacks. In this presentation, we leverage the techniques of AT to evaluate/enhance the reliabilities of some AI tools, such as image denoiser and non-parametric two-sample tests. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Adversarial robustness |
Paper # | NC2022-4,IBISML2022-4 |
Date of Issue | 2022-06-20 (NC, IBISML) |
Conference Information | |
Committee | NC / IBISML / IPSJ-BIO / IPSJ-MPS |
---|---|
Conference Date | 2022/6/27(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Hiroshi Yamakawa(Univ of Tokyo) / Masashi Sugiyama(Univ. of Tokyo) |
Vice Chair | Hirokazu Tanaka(Tokyo City Univ.) / Toshihiro Kamishima(AIST) / Koji Tsuda(Univ. of Tokyo) |
Secretary | Hirokazu Tanaka(NTT) / Toshihiro Kamishima(NICT) / Koji Tsuda(NTT) / (Hokkaido Univ.) |
Assistant | Yoshimasa Tawatsuji(Waseda Univ.) / Tomoki Kurikawa(KMU) / Yoshinobu Kawahara(Osaka Univ.) / Taiji Suzuki(Tokyo Inst. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Bioinformatics and Genomics / Special Interest Group on Mathematical Modeling and Problem Solving |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Evaluating and Enhancing Reliabilities of AI-Powered Tools |
Sub Title (in English) | Adversarial Robustness |
Keyword(1) | Adversarial robustness |
1st Author's Name | Jingfeng Zhang |
1st Author's Affiliation | RIKEN Center for Advanced Intelligence Project(RIKEN-AIP) |
Date | 2022-06-27 |
Paper # | NC2022-4,IBISML2022-4 |
Volume (vol) | vol.122 |
Number (no) | NC-89,IBISML-90 |
Page | pp.pp.20-46(NC), pp.20-46(IBISML), |
#Pages | 27 |
Date of Issue | 2022-06-20 (NC, IBISML) |