Research talk: Can causal learning improve the privacy of ML models?
298
Microsoft Research334 тыс
Следующее
Популярные
174 дня – 22215:51
24.03.23 – 2 1245:38Опубликовано 8 февраля 2022, 17:15
Speaker: Shruti Tople, Senior Researcher, Microsoft Research Cambridge
Ensuring privacy of data used to train machine learning models is important for safe and responsible deployment of these models. At the same time, models are required to generalize across different data distributions to enable widespread adoption. Balancing this privacy-utility trade-off has been a key challenge in designing privacy-preserving ML solutions.
In this talk, senior researcher Shruti Tople, from the Confidential Computing team at Microsoft Research Cambridge, will discuss well-known privacy attacks, such as membership inference, and show how causal learning techniques can play an important role in enhancing privacy guarantees of ML models.
Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit
Ensuring privacy of data used to train machine learning models is important for safe and responsible deployment of these models. At the same time, models are required to generalize across different data distributions to enable widespread adoption. Balancing this privacy-utility trade-off has been a key challenge in designing privacy-preserving ML solutions.
In this talk, senior researcher Shruti Tople, from the Confidential Computing team at Microsoft Research Cambridge, will discuss well-known privacy attacks, such as membership inference, and show how causal learning techniques can play an important role in enhancing privacy guarantees of ML models.
Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit
Свежие видео
2 дня – 1 720 4110:39
3 дня – 3 5831:46
3 дня – 6560:25
5 дней – 8531:53
10 дней – 35 20214:32Случайные видео
6 дней – 960:27
219 дней – 23 7528:45
299 дней – 27 161 46037:19
19.11.23 – 3 9573:16
18.05.23 – 89 7469:24
08.10.14 – 144 9436:53
2 дня – 977 54718:29
4 дня – 40 81927:39
5 дней – 7070:49
10 дней – 8140:15
12 дней – 32013:12
14 дней – 101 8332:58
