| 研究課題/領域番号 |
20K19824
|
|---|
| 研究機関 | 九州大学 |
|---|
研究代表者 |
VARGAS DANILO 九州大学, システム情報科学研究院, 准教授 (00795536)
|
|---|
| 研究期間 (年度) |
2020-04-01 – 2022-03-31
|
| キーワード | 敵対的機械学習 / Deep Neural Networks / 深層学習 / One pixel attack |
|---|
| 研究実績の概要 |
The planned architecture was developed and tested. The improvement of the robustness was also verified. Variations of the architecture using generative neural networks and autoencoders were realized and tested. It was also proposed new methods to evaluate the latent space of variables in both autoencoders and layers of deep neural networks. All these results were described in detail and submitted/published in papers.
Regarding the research achievements, 7 papers in international conferences and 1 book was published. Additionally, there were an invited talk about the subject and 2 tutorials in top conferences such as IJCAI and WCCI.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
1: 当初の計画以上に進展している
理由
Research experiments could be finished without great problems, leading to a more smooth than initially planned status. Currently most of the research was/is being submitted to top conferences.
|
| 今後の研究の推進方策 |
This year beyond finishing the last part of the planned research, other types of robust architectures/paradigms for computer vision will be also investigated.
|
| 次年度使用額が生じた理由 |
COVID-19の影響に応じて、必要でした。
|
