| Presentation | 2023-11-10 Zero-Knowledge Proofs for ownership of Deep Neural Network Shungo Sato, Hidema Tanaka, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Because AI technologies have rapidly spread and developed in our society, Neural Networks, which are one of Machine Learning, are used in various fields such as research and development. Since it takes much time and cost to make high-performance models for use, we tune a trained model in order to make the model for our purpose more efficiently. Hence, it is important to share high-performance trained models for the development of AI technologies. In the case of sharing a trained model, it is important to protect its ownership for the owners. In this paper, we propose a method of protecting ownership of a model by using zero-knowledge proofs. By our proposal, owners can protect ownership of their trained model and claim the right to tuned models. We can also show that it can sufficiently lower the probability of spoofing if the variables are chosen appropriately in the setup. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | AI / Machine Learning / DNN / ownership / ZKP / STARK |
| Paper # | ISEC2023-67,SITE2023-61,LOIS2023-25 |
| Date of Issue | 2023-11-02 (ISEC, SITE, LOIS) |
| Conference Information | |
| Committee | LOIS / SITE / ISEC |
|---|---|
| Conference Date | 2023/11/9(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Satellite Campus Hiroshima |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Hiroyuki Toda(NTT) / Takushi Otani(Kibi International Univ.) / Goichiro Hanaoka(AIST) |
| Vice Chair | Manabu Motegi(Takushoku Univ.) / Soichiro Morishita(Cyber Agent) / Takeo Tatsumi(Open Univ. of Japan) / Junji Shikata(Yokohama National Univ.) / Shinsaku Kiyomoto(KDDI Research) |
| Secretary | Manabu Motegi(Nagasaki Univ.) / Soichiro Morishita(NTT) / Takeo Tatsumi(NRI-Secure) / Junji Shikata(Fukuoka Inst. of Tech.) / Shinsaku Kiyomoto(AIST) |
| Assistant | Makoto Takita(Univer. of Hyogo) / Yusuke Kaneko(Japan Research Institute) / Hiroki Okada(KDDI Research) |
| Paper Information | |
| Registration To | Technical Committee on Life Intelligence and Office Information Systems / Technical Committee on Social Implications of Technology and Information Ethics / Technical Committee on Information Security |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Zero-Knowledge Proofs for ownership of Deep Neural Network |
| Sub Title (in English) | |
| Keyword(1) | AI |
| Keyword(2) | Machine Learning |
| Keyword(3) | DNN |
| Keyword(4) | ownership |
| Keyword(5) | ZKP |
| Keyword(6) | STARK |
| 1st Author's Name | Shungo Sato |
| 1st Author's Affiliation | National Defense Academy of Japan(NDA) |
| 2nd Author's Name | Hidema Tanaka |
| 2nd Author's Affiliation | National Defense Academy of Japan(NDA) |
| Date | 2023-11-10 |
| Paper # | ISEC2023-67,SITE2023-61,LOIS2023-25 |
| Volume (vol) | vol.123 |
| Number (no) | ISEC-245,SITE-246,LOIS-247 |
| Page | pp.pp.86-92(ISEC), pp.86-92(SITE), pp.86-92(LOIS), |
| #Pages | 7 |
| Date of Issue | 2023-11-02 (ISEC, SITE, LOIS) |