justhsu
/
cs763
Archived
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Tweak slides.

This commit is contained in:
Justin Hsu 2019-09-04 13:47:29 -05:00
parent 959588648e
commit a94a9f9d53
1 changed files with 33 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
website/docs/resources/slides/lecture-welcome.md
View File

@ -14,10 +14,6 @@ date: September 04, 2019
![](images/broken.png) ![](images/broken.png)
## It's really difficult!
![](images/netflix.png)
# What topics to cover? # What topics to cover?
## A really, really vast field ## A really, really vast field
@ -173,7 +169,7 @@ date: September 04, 2019
## Todos for you ## Todos for you
0. Complete the [course survey](https://forms.gle/NvYx3BM7HVkuzYdG6) 0. Complete the [course survey](https://forms.gle/NvYx3BM7HVkuzYdG6)
1. Explore the [course website](https://pages.cs.wisc.edu/~justhsu/teaching/current/cs763/) 1. Explore the [course website](https://pages.cs.wisc.edu/~justhsu/teaching/current/cs763/)
2. Think about which lecture you want to present and summarize 2. Think about which lecture you want to present
3. Think about which lecture you want to summarize 3. Think about which lecture you want to summarize
4. Form project groups and brainstorm topics 4. Form project groups and brainstorm topics
@ -217,10 +213,28 @@ date: September 04, 2019
- Really, really hard to think about side information - Really, really hard to think about side information
- May not even be public at time of data release! - May not even be public at time of data release!
## Netflix challenge ## Netflix prize
- Database of movie ratings - Database of movie ratings
- Published: ID number, movie rating, and rating date - Published: ID number, movie rating, and rating date
- Attack: from public IMDB ratings, recover names for Netflix data - Competition: predict which movies IDs will like
- Result
- Tons of teams competed
- Winner: beat Netflix's best by **10%**
> A triumph for machine learning contests!
##
![](images/netflix.png)
## Privacy flaw?
- Attack
- Public info on IMDB: names, ratings, dates
- Reconstruct names for Netflix IDs
- Result
- Netflix settled lawsuit ($10 million)
- Netflix canceled future challenges
## "Blending in a crowd" ## "Blending in a crowd"
- Only release records that are similar to others - Only release records that are similar to others
@ -233,14 +247,17 @@ date: September 04, 2019
- First few queries fine, then suddenly total violation - First few queries fine, then suddenly total violation
- Again, interacts poorly with side-information - Again, interacts poorly with side-information
## Differential privacy # Differential privacy
- Proposed by Dwork, McSherry, Nissim, Smith (2006)
## Yet another privacy definition
> A new approach to formulating privacy goals: the risk to one’s privacy, or in > A new approach to formulating privacy goals: the risk to one’s privacy, or in
> general, any type of risk... should not substantially increase as a result of > general, any type of risk... should not substantially increase as a result of
> participating in a statistical database. This is captured by differential > participating in a statistical database. This is captured by differential
> privacy. > privacy.
- Proposed by Dwork, McSherry, Nissim, Smith (2006)
## Basic setting ## Basic setting
- Private data: set of records from individuals - Private data: set of records from individuals
- Each individual: one record - Each individual: one record
@ -256,3 +273,10 @@ subset $S$ of outputs, we have:
$$ $$
\Pr[ Q(db) \in S ] \leq e^\varepsilon \cdot \Pr[ Q(db') \in S ] + \delta \Pr[ Q(db) \in S ] \leq e^\varepsilon \cdot \Pr[ Q(db') \in S ] + \delta
$$ $$
## Basic reading
> Output of program doesn't depend too much on any single person's data
- Property of the algorithm/query/program
- No: "this data is differentially private"
- Yes: "this query is differentially private"