| Presentation | 2020-11-25 GAN based feature-level supportive method for improved adversarial attacks on face recognition Zhengwei Yin, Kaoru Uchida, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | With the rapid development of deep neural networks (DNN), DNN-based face recognition technologies are also achieving great success and have been widely used in various applications which require high-accuracy and robustness. However, deep neural networks are known to be vulnerable to adversarial attacks, performed using images added with well-designed perturbations. To enhance security of DNN-based face recognition, we need to explore deeper the mechanisms of related technologies. In this paper, we propose a feature-level supportive method, BiasGAN, to improve the performance of universal adversarial attack methods. We insert this image to image translation preprocessor before conducting adversarial example generation. BiasGAN will search in the potential face space and can generate images with biased face feature, causing generated face images to be easier to perturb efficiently. Experimental results show that this approach improves both fooling ratio and average perturbation size significantly at different perturbation levels. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep neural network / enerative adversarial network / Face recognition / Adversarial attack |
| Paper # | BioX2020-35 |
| Date of Issue | 2020-11-18 (BioX) |
| Conference Information | |
| Committee | BioX |
|---|---|
| Conference Date | 2020/11/25(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Akira Otsuka(AIST) |
| Vice Chair | Takahiro Aoki(Fujitsu Labs.) / Masatsugu Ichino(Univ. of Electro-Comm.) |
| Secretary | Takahiro Aoki(SECOM) / Masatsugu Ichino(KDDI Research) |
| Assistant | Emiko Sano(MitsubishiElectric) / Akihiro Hayasaka(NEC) |
| Paper Information | |
| Registration To | Technical Committee on Biometrics |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | GAN based feature-level supportive method for improved adversarial attacks on face recognition |
| Sub Title (in English) | |
| Keyword(1) | Deep neural network |
| Keyword(2) | enerative adversarial network |
| Keyword(3) | Face recognition |
| Keyword(4) | Adversarial attack |
| 1st Author's Name | Zhengwei Yin |
| 1st Author's Affiliation | University of Science and Technology of China/Hosei University(USTC/Hosei Univ.) |
| 2nd Author's Name | Kaoru Uchida |
| 2nd Author's Affiliation | Hosei University(Hosei Univ.) |
| Date | 2020-11-25 |
| Paper # | BioX2020-35 |
| Volume (vol) | vol.120 |
| Number (no) | BioX-247 |
| Page | pp.pp.1-6(BioX), |
| #Pages | 6 |
| Date of Issue | 2020-11-18 (BioX) |