Security of Machine Learning
- Hold Date
- 2019-07-10 16:45~2019-07-10 17:45
- Place
- IMI Auditorium (W1-D-413), West Zone 1, Ito campus, Kyushu University
- Object person
-
- Speaker
-
Satsuya OHATA (National Institute of Advanced Industrial Science and Technology (AIST))
The IMI Colloquium in July | Date : Wednesday, 10 July 2019 16:45-17:45 | Place : IMI Auditorium (W1-D-413) (4F, West Zone 1, Kyushu University) | | Speaker : Dr. Satsuya OHATA (National Institute of Advanced Industrial Science and Technology (AIST)) | | Title : | Security of Machine Learning | | Abstract : In security research, we have been frequently used machine learning techniques as tools. Recently, we can also see many research results on the security for machine learning itself. In this talk, we introduce research results on machine learning security. I will mainly explain the specially-crafted image/signal called adversarial examples. Moreover, I also roughly talk about other results in this research field (model extraction, model inversion, and membership inferences, etc.). | | | IMI Colloquium Report |