cs763/website/docs/resources/slides/lecture-welcome.md

---
author: Security and Privacy in Data Science (CS 763)
title: Course Welcome
date: September 04, 2019
---

# Security and Privacy

## It's everywhere!

![](images/iot-cameras.png)

## Stuff is totally insecure!

![](images/broken.png)

# What topics to cover?

## A really, really vast field
- Things we will not be able to cover:
    - Real-world attacks
    - Computer systems security
    - Defenses and countermeasures
    - Social aspects of security
    - Theoretical cryptography
    - ...

## Theme 1: Formalizing S&P
- Mathematically formalize notions of security
- Rigorously prove security
- Guarantee that certain breakages can't occur

> Remember: definitions are tricky things!

## Theme 2: Automating S&P
- Use computers to help build more secure systems
- Automatically check security properties
- Search for attacks and vulnerabilities

## Five modules
1. Differential privacy
2. Adversarial machine learning
3. Crytpography in machine learning
4. Algorithmic fairness
5. PL and verification

## This course is broad!
- Each module could be its own course
    - We won't be able to go super deep
    - You will probably get lost
- Our goal: broad survey of multiple areas
    - Lightning tour, focus on high points

>  Hope: find a few things that interest you

## This course is technical!
- Approach each topic from a rigorous point of view
- Parts of "data science" with **provable guarantees**
- This is not a "theory course", but...

. . .

![](images/there-will-be-math.png)

# Differential privacy

##

![](images/privacy.png)

## A mathematically solid definition of privacy
- Simple and clean formal property
- Satisfied by many algorithms
- Degrades gracefully under composition

# Adversarial machine learning

##

![](images/aml.jpg)

## Manipulating ML systems
- Crafting examples to fool ML systems
- Messing with training data
- Extracting training information

# Cryptography in machine learning

##

![](images/crypto-ml.png)

## Crypto in data science
- Learning models without raw access to private data
- Collecting analytics data privately, at scale
- Side channels and implementation issues
- Verifiable execution of ML models
- Other topics (e.g., model watermarking)

# Algorithmic fairness

##

![](images/fairness.png)

## When is a program "fair"?
- Individual and group fairness
- Inherent tradeoffs and challenges
- Fairness in unsupervised learning
- Fairness and causal inference

# PL and verification

##

![](images/pl-verif.png)

## Proving correctness
- Programming languages for security and privacy
- Interpreting neural networks and ML models
- Verifying properties of neural networks
- Verifying probabilistic programs

# Tedious course details

## Lecture schedule
- First ten weeks: **lectures MWF**
    - Intensive lectures, get you up to speed
    - M: I will present
    - WF: You will present
- Last five weeks: **no lectures**
    - Intensive work on projects
    - I will be available to meet, one-on-one

> You must attend lectures and participate

## Class format
- Three components:
    1. Paper presentations
    2. Presentation summaries
    3. Final project
- Announcement/schedule/materials: on [website](https://pages.cs.wisc.edu/~justhsu/teaching/current/cs763/)
- Class mailing list: [compsci763-1-f19@lists.wisc.edu]()

## Paper presentations
- In pairs, lead a discussion on group of papers
    - See website for [detailed instructions](https://pages.cs.wisc.edu/~justhsu/teaching/current/cs763/assignments/presentations/jjj)
    - See website for [schedule of topics](https://pages.cs.wisc.edu/~justhsu/teaching/current/cs763/schedule/lectures/)
- One week **before** presentation: meet with me
    - Come prepared with presentation materials
    - Run through your outline, I will give feedback

## Presentation summaries
- In pairs, prepare written summary of another group
    - See website for [detailed instructions](https://pages.cs.wisc.edu/~justhsu/teaching/current/cs763/assignments/summaries/)
    - See website for [schedule of topics](https://pages.cs.wisc.edu/~justhsu/teaching/current/cs763/schedule/lectures/)
- One week **after** presentation: send me summary
    - I will work with you to polish report
    - Writeups will be shared with the class

## Final project
- In groups of three (or very rarely two)
- See website for [project details](https://pages.cs.wisc.edu/~justhsu/teaching/current/cs763/assignments/project/)
- Key dates:
    - **October 11**: Milestone 1
    - **November 8**: Milestone 2
    - **End of class**: Final writeups and presentations

## Todos for you
0. Complete the [course survey](https://forms.gle/NvYx3BM7HVkuzYdG6)
1. Explore the [course website](https://pages.cs.wisc.edu/~justhsu/teaching/current/cs763/)
2. Think about which lecture you want to present
3. Think about which lecture you want to summarize
4. Form project groups and brainstorm topics

> Signup for slots and projects [here](https://docs.google.com/spreadsheets/d/1hSbRy0mo3PjlozN0Ph1JkP5JwlRG8y7ukuCdorofncA/edit?usp=sharing)

## We will move quickly
- First deadline: **next Monday, September 9**
    - Form paper and project groups
    - Signup sheet [here](https://docs.google.com/spreadsheets/d/1hSbRy0mo3PjlozN0Ph1JkP5JwlRG8y7ukuCdorofncA/edit?usp=sharing) 
    - Please: don't sign up for the same slot
- First slot is soon: **next Friday, September 13**
    - Only slot for presenting differential privacy
    - I will help the first group prepare

# Defining privacy

## What does privacy mean?
- Many kinds of "privacy breaches"
    - Obvious: third party learns your private data
    - Retention: you give data, company keeps it forever
    - Passive: you don't know your data is collected

## Why is privacy hard?
- Hard to pin down what privacy means!
- Once data is out, can't put it back into the bottle
- Privacy-preserving data release today may violate privacy tomorrow, combined
  with "side-information"
- Data may be used many times, often doesn't change

## Hiding private data
- Delete "personally identifiable information"
    - Name and age
    - Birthday
    - Social security number
    - ...
- Publish the "anonymized" or "sanitized" data

## Problem: not enough
- Can match up anonymized data with public sources
- *De-anonymize* data, associate names to records
- Really, really hard to think about side information
    - May not even be public at time of data release!

## Netflix prize
- Database of movie ratings
- Published: ID number, movie rating, and rating date
- 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"
- Only release records that are similar to others
- *k-anonymity*: require at least k identical records
- Other variants: *l-diversity*, *t-closeness*, ...

## Problem: composition
- Repeating k-anonymous releases may lose privacy
- Privacy protection may fall off a cliff
    - First few queries fine, then suddenly total violation
- Again, interacts poorly with side-information

# Differential privacy

## Yet another privacy definition

> 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
> participating in a statistical database.  This is captured by differential
> privacy.

- Proposed by Dwork, McSherry, Nissim, Smith (2006)

## Basic setting
- Private data: set of records from individuals
    - Each individual: one record
    - Example: set of medical records
- Private query: function from database to output
    - Randomized: adds noise to protect privacy

## Basic definition
A query $Q$ is **$(\varepsilon, \delta)$-differentially private** if for every two
databases $db, db'$ that differ in **one individual's record**, and for every
subset $S$ of outputs, we have:

$$
\Pr[ Q(db) \in S ] \leq e^\varepsilon \cdot \Pr[ Q(db') \in S ] + \delta
$$

## 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"