Start updating course webpage.

This commit is contained in:
Justin Hsu 2019-07-30 18:18:30 -05:00
parent f0395fb764
commit b255bfa101
6 changed files with 83 additions and 81 deletions

View File

@ -1,21 +1,20 @@
# Project Details # Project Details
The goal of the course project is to dive more deeply into a particular topic. The goal of the course project is to dive more deeply into a particular topic.
The project can be completed either **individually** or in **groups of two**. A The project can be completed in **groups of two or three**. A good project could
good project could potentially lead to a publishable result. This project could lead to some kind of publication. This project could take different forms:
take different forms:
- **Conceptual**: Extend a technique or explore a new application. - **Conceptual**: Develop a new technique, extend an existing method, or explore
- **Experience report**: Experiment with an existing implementation, trying out a new application
different examples and describing the overall experience. Or make a new - **Experience report**: Experiment with an implementation, trying out different
implementation. examples and describing the overall experience. Or implement something new.
- **Literature survey**: Select a couple (3-5) of related papers in a recent - **Literature survey**: Select a couple (3-5) of closely related papers in a
research area. Summarize the significance, then compare and contrast. recent research area. Summarize the significance, then compare and contrast.
- **Other**: Feel free to propose other kinds of projects. - **Other**: Feel free to propose other kinds of projects.
If at any point you have trouble finding a project, run into difficulties, or If at any point you have trouble finding a project, run into difficulties, or
just want some advice, **please come talk to me** and I will try to help you get just don't know what to do, **please come talk to me as soon as possible** and I
unstuck. will help you get unstuck.
## Deliverables ## Deliverables
@ -38,8 +37,7 @@ should be clear what remains to be done.
Besides the milestones, the main deliverable of the project will be a written Besides the milestones, the main deliverable of the project will be a written
final report, around **15-20 pages** in length. Reports should be written in a final report, around **15-20 pages** in length. Reports should be written in a
research paper style, covering the following broad areas in some reasonable research paper style, covering the following areas in some reasonable order:
order:
- **Introduce** the problem and the motivation. - **Introduce** the problem and the motivation.
- **Review** background and preliminary material. - **Review** background and preliminary material.
@ -47,8 +45,7 @@ order:
- **Evaluate** the results. - **Evaluate** the results.
- **Survey** related work. - **Survey** related work.
At the end of the course, each group will give a brief project presentation in At the end of the course, each group will give a brief project presentation.
class.
## Deadlines ## Deadlines

View File

@ -1,32 +1,36 @@
# Welcome to CS 839! # Welcome to CS 763!
This is a graduate-level course covering advanced topics in security and This is a graduate-level course covering advanced topics in security and privacy
privacy. We will focus on four areas at the current research frontier: (1) in data science. We will focus on four areas at the current research frontier:
differential privacy, (2) applied cryptography, (3) language-based security, and (1) differential privacy, (2) applied cryptography, (3) language-based security,
(4) adversarial machine learning. Students will read, present, and discuss and (4) adversarial machine learning. Students will read, present, and discuss
papers from the research literature (i.e., conference and journal papers), and papers from the research literature (i.e., conference and journal papers), and
complete a final project. complete a final project.
## Logistics ## Logistics
- **Course**: CS 839, Fall 2018 - **Course**: CS 763, Fall 2019
- **Location**: CS 1325 - **Location**: CS 1263
- **Time**: Mondays and Wednesdays, 4:00-5:15 - **Time**: Monday, Wednesday, Friday, 2:00-3:15
For the first ten weeks, lectures will be held on Monday, Wednesday, and Friday.
In the remaining five weeks, you will work on your course projects. Though there
are no lectures scheduled in this period, I am available to meet as needed.
## Mailing List ## Mailing List
Please use the mailing list if you want to contact the whole course: Please use the mailing list if you want to contact the whole course:
- [compsci839-1-f18@lists.wisc.edu](compsci839-1-f18@lists.wisc.edu) - <mailto:compsci763-1-f19@lists.wisc.edu>
All registered students should be on this list. If you are not registered but All registered students should be on this list. If you are not registered but
would like to follow along, please let me know and I will try to add you. would like to follow along, please let me know and I will add you.
Otherwise, you can contact me directly. To ensure that your email goes to the Otherwise, you can contact me directly. To ensure that your email goes to the
right place, please start the subject with **CS839**. right place, please start the subject with **CS763**.
## Course Staff ## Course Staff
- **Instructor**: [Justin Hsu](https://justinh.su) - **Instructor**: [Justin Hsu](https://justinh.su)
- **Email**: justhsu@cs.wisc.edu - **Email**: <mailto:justhsu@cs.wisc.edu>
- **Location**: CS 6379 - **Location**: CS 6379
- **Office hours**: By appointment - **Office hours**: By appointment

View File

@ -1,9 +1,7 @@
Lectures will be loosely organized around four **modules**: differential Lectures will be loosely organized around three core modules: differential
privacy, applied cryptography, language-based security, and adversarial machine privacy, adversarial machine learning, and applied cryptography. We will also
learning. I will give most of the lectures for the first module (differential cover two advanced modules: algorithmic fairness, and PL and verification
privacy). For the other modules, I will give an overview lecture surveying the techniques.
topic and background material. Then, each student will lead one lecture,
presenting a paper and guiding the discussion.
This is a graduate seminar, so not all lectures are set in stone and there is This is a graduate seminar, so not all lectures are set in stone and there is
considerable flexibility in the material. If you are interested in something not considerable flexibility in the material. If you are interested in something not
@ -34,6 +32,12 @@ a few sentences per question. These questions will help you check that you have
understood the papers---they are not meant to be very difficult or understood the papers---they are not meant to be very difficult or
time-consuming and they will not be graded in detail. time-consuming and they will not be graded in detail.
## Course Materials
For differential privacy, we will use the textbook *Algorithmic Foundations of
Data Privacy* (AFDP) by Cynthia Dwork and Aaron Roth, available
[here](https://www.cis.upenn.edu/~aaroth/Papers/privacybook.pdf).
## Course Project ## Course Project
The other main component is the **course project**. You will work individually The other main component is the **course project**. You will work individually

View File

@ -1,4 +1,4 @@
The first key date is **September 19**. Before this date, you should: The first key date is **September 16**. By this date, you should:
- **Check in** with me briefly. - **Check in** with me briefly.
- **Sign up** to present a paper. - **Sign up** to present a paper.
@ -6,6 +6,6 @@ The first key date is **September 19**. Before this date, you should:
you should have an initial direction. you should have an initial direction.
## Project Deadlines ## Project Deadlines
- Milestone 1: **October 17** - Milestone 1: **October 7**
- Milestone 2: **November 14** - Milestone 2: **November 8**
- Final writeup and presentation: **December 14** - Final writeup and presentation: **December 11** (TBD)

View File

@ -1,43 +1,40 @@
# Calendar (Tentative) # Calendar
For differential privacy, we will use the textbook *Algorithmic Foundations of Date | Topic | Notes
Data Privacy* (AFDP) by Cynthia Dwork and Aaron Roth, available
[here](https://www.cis.upenn.edu/~aaroth/Papers/privacybook.pdf).
Date | Topic | Presenter
:----:|-------|:---------: :----:|-------|:---------:
| <center> <h4> **Differential Privacy** </h4> </center> | | <center> <h4> **Differential Privacy** </h4> </center> |
9/5 | [Course welcome, introducing differential privacy](../resources/slides/lecture-welcome.html) <br> **Paper:** Keshav. [*How to Read a Paper*](https://web.stanford.edu/class/ee384m/Handouts/HowtoReadPaper.pdf). | Justin 9/4 | [Course welcome](../resources/slides/lecture-welcome.html) <br> **Paper:** Keshav. [*How to Read a Paper*](https://web.stanford.edu/class/ee384m/Handouts/HowtoReadPaper.pdf). |
9/10 | Basic private mechanisms <br> **Reading:** AFDP 3.2, 3.3 | Justin 9/6 | |
9/12 | Composition and closure properties <br> **Reading:** AFDP 3.5 | Justin 9/9 | |
9/17 | What does differential privacy actually mean? <br> **Reading:** McSherry. [*Lunchtime for Differential Privacy*](https://github.com/frankmcsherry/blog/blob/master/posts/2016-08-16.md) (see also these [two](https://github.com/frankmcsherry/blog/blob/master/posts/2016-06-14.md) [posts](https://github.com/frankmcsherry/blog/blob/master/posts/2016-08-29.md)) | Justin 9/11 | |
9/19 | Exponential mechanism <br> **Paper:** McSherry and Talwar. [*Mechanism Design via Differential Privacy*](http://kunaltalwar.org/papers/expmech.pdf). <br> <center> <h5> **Due: Project topics and groups** </h5> </center> | Justin 9/13 | |
**9/21 (FRI)** | Identity-Based Encryption from the Diffie-Hellman Assumption <br> <center> **SPECIAL TIME AND PLACE: 4 PM, CS 1240** </center> | Sanjam Garg
9/24 | Advanced mechanisms <br> Report-noisy-max, Sparse Vector Technique, and Private Multiplicative Weights <br> **Reading:** AFDP 3.3, 3.5, 4.2 | Justin
9/26 | Privacy for data streams <br> **Paper:** Chan, Shi, and Song. [*Private and Continual Release of Statistics*](https://eprint.iacr.org/2010/076.pdf). | Yinglun
10/1 | Local differential privacy <br> **Paper:** Erlingsson, Pihur, and Korolova. [*RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response*](https://arxiv.org/pdf/1407.6981.pdf). | Justin
| <center> <h4> **Adversarial Machine Learning** </h4> </center> | | <center> <h4> **Adversarial Machine Learning** </h4> </center> |
10/3 | [AML: overview and basics](../resources/slides/somesh-aml.pdf) <br> <center> **GUEST LECTURE** </center> | Somesh Jha 9/16 | |
10/8 | History of Adversarial ML <br> **Paper:** Biggio and Roli. [*Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning*](https://arxiv.org/pdf/1712.03141). | Meghana 9/18 | |
10/10 | Adversarial examples <br> **Paper:** Szegedy, Zaremba, Sutskever, et al. [*Intriguing Properties of Neural Networks*](https://arxiv.org/pdf/1312.6199.pdf). | Shimaa 9/20 | |
10/15 | <center> **NO CLASS: INSTRUCTOR AWAY** </center> | 9/23 | |
10/17 | <center> **NO CLASS: INSTRUCTOR AWAY** <br> <center> <h5> **Due: Milestone 1** </h5> </center> | 9/25 | |
10/22 | Adversarial examples <br> **Paper:** Goodfellow, Schlens, and Szegedy. [*Explaining and Harnessing Adversarial Examples*](https://arxiv.org/abs/1412.6572). | Kyrie 9/27 | |
10/24 | Real-world attacks <br> **Paper:** Eykholt, Evtimov, Fernandes, et al. [*Robust Physical-World Attacks on Deep Learning Models*](https://arxiv.org/pdf/1707.08945.pdf). | Hiba | <center> <h4> **Applied Cryptography** </h4> </center> |
10/29 | Detection methods <br> **Paper:** Carlini and Wagner. [*Towards Evaluating the Robustness of Neural Networks*](https://arxiv.org/pdf/1608.04644.pdf). | Yiqin 9/30 | |
10/31 | Detection methods <br> **Paper:** Carlini and Wagner. [*Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods*](https://arxiv.org/pdf/1705.07263.pdf). | Junxiong 10/2 | |
11/5 | Defensive measures <br> **Paper:** Steinhardt, Koh, and Liang. [*Certified Defenses for Data Poisoning Attacks*](https://arxiv.org/pdf/1706.03691.pdf). | Yaman 10/4 | |
11/7 | Defensive measures <br> **Paper:** Madry, Makelov, Schmidt, Schmidt, Tsipras, and Valdu. [*Towards Deep Learning Models Resistant to Adversarial Attacks*](https://arxiv.org/pdf/1706.06083.pdf). | Maddie 10/7 | |
| <center> <h4> **Cryptographic Techniques** </h4> </center> | 10/9 | |
11/12 | Applied crypto: overview and basics | Justin 10/11 | |
11/14 | Verifiable differential privacy <br> **Paper:** Narayan, Feldman, Papadimitriou, and Haeberlen. [*Verifiable Differential Privacy*](https://www.cis.upenn.edu/~ahae/papers/verdp-eurosys2015.pdf). <br> <center> <h5> **Due: Milestone 2** </h5> </center> | Fayi | <center> <h4> **Advanced Topic: Algorithmic Fairness** </h4> </center> |
11/19 | Homomorphic encryption <br> **Paper:** Halevi and Shoup. [*Algorithms in HElib*](https://www.shoup.net/papers/helib.pdf). | Yue 10/14 | |
| <center> <h4> **Language-Based Security** </h4> </center> | 10/16 | |
11/21 | [Language-based security: overview and basics](../resources/slides/lecture-langsec.html) | Justin 10/18 | |
11/26 | Languages for privacy <br> **Paper:** Reed and Pierce. [*Distance Makes the Types Grow Stronger: A Calculus for Differential Privacy*](https://www.cis.upenn.edu/~bcpierce/papers/dp.pdf). | Sam 10/21 | |
11/28 | Cryptε: Crypto-Assisted Differential Privacy <br> <center> **GUEST LECTURE** </center> | Amrita Roy Chowdhury 10/23 | |
12/3 | Languages for authenticated datastructures <br> **Paper:** Miller, Hicks, Katz, and Shi. [*Authenticated Data Structures, Generically*](https://www.cs.umd.edu/~mwh/papers/gpads.pdf). | Zichuan 10/25 | |
12/5 | Languages for oblivous computing <br> **Paper:** Zahur and Evans. [*Obliv-C: A Language for Extensible Data-Oblivious Computation*](https://eprint.iacr.org/2015/1153.pdf). | Zhiyi | <center> <h4> **Advanced Topic: PL and Verification** </h4> </center> |
12/10 | Languages for information flow <br> **Paper:** Griffin, Levy, Stefan, et al. [*Hails: Protecting Data Privacy in Untrusted Web Applications*](https://www.usenix.org/system/files/conference/osdi12/osdi12-final-35.pdf). | Arjun 10/28 | |
12/12 | Timing channels <br> **Paper:** Wang, Ferraiuolo, Zhang, Myers, and Suh. [*SecDCP: Secure Dynamic Cache Partitioning for Efficient Timing Channel Protection*](http://www.csl.cornell.edu/~yao/docs/DAC2016.pdf). | Yan 10/30 | |
**12/14 (FRI)** | Project presentations <br> <center> **SPECIAL TIME AND PLACE: 10 AM, CS 2310** </center> <center> <h5> **Due: Final project reports** </h5> </center> | 11/1 | |
11/4 | |
11/6 | |
11/8 | |
| <center> <h4> **No Lectures: Work on Projects** </h4> </center> |
12/11 (TBD) | Project Presentations |

View File

@ -1,7 +1,7 @@
site_name: 'CS 839: Topics in Security and Privacy Technologies (Fall 2018)' site_name: 'CS 763: Security and Privacy in Data Science (Fall 2019)'
site_url: '' site_url: ''
repo_url: 'https://git.justinh.su/justhsu/cs839' repo_url: 'https://git.justinh.su/justhsu/cs763'
site_description: 'Course webpage for CS 839: Topics in Security and Privacy Technologies (Fall 2018)' site_description: 'Course webpage for CS 763: Security and Privacy in Data Science (Fall 2019)'
site_author: 'Justin Hsu' site_author: 'Justin Hsu'
theme: theme:
@ -12,8 +12,8 @@ theme:
logo: 'assets/images/favicon.ico' logo: 'assets/images/favicon.ico'
favicon: 'assets/images/favicon.ico' favicon: 'assets/images/favicon.ico'
palette: palette:
primary: blue grey primary: red
accent: blue grey accent: red
nav: nav:
- Home: - Home: