關於這一集
Strachey Lecture: Privacy, Verification, Robustness: A Cryptographer's perspective on ML Cryptographic tools enable the safe use of technology platforms controlled by worst case computationally bounded adversaries.In this talk I will show how cryptographic paradigms and tools can be used to address trust issues in various phases of the machine learning pipeline. We will touch on approaches for achieving privacy, correctness, and robustness in presence of adversaries.
英語
英國
在這一集裡
逐字稿 🔗
1
00:00:01,090 --> 00:00:05,310
[Auto-generated transcript. Edits may have been applied for clarity.]
So. If you haven't.
2
00:00:13,700 --> 00:00:20,470
Okay. Um, I'd like to welcome everybody to this chance is screen Lecture, which is our distinguished lecture.
3
00:00:20,480 --> 00:00:29,570
Um, before I introduce the speaker, one of our sponsors of progressive content, uh, who has been hosting this series since 2015.
4
00:00:30,170 --> 00:00:34,250
And if any students or researchers want …
00:00:01,090 --> 00:00:05,310
[Auto-generated transcript. Edits may have been applied for clarity.]
So. If you haven't.
2
00:00:13,700 --> 00:00:20,470
Okay. Um, I'd like to welcome everybody to this chance is screen Lecture, which is our distinguished lecture.
3
00:00:20,480 --> 00:00:29,570
Um, before I introduce the speaker, one of our sponsors of progressive content, uh, who has been hosting this series since 2015.
4
00:00:30,170 --> 00:00:34,250
And if any students or researchers want …
免責聲明: 本頁面嵌入的 Podcast 和封面圖片來自 Oxford University,歸其所有者所有,與 Listen Notes, Inc. 無關聯,也未獲得 Listen Notes, Inc. 背書。