Privacy Enhancing Technologies Yang Zhang

News

20.08.2020

PETS Results Are Out

Dear all,

The final grade has been finalized and you can check them on LSF.

Again, thanks a lot for staying with us during the whole semester, I wish you all a good summer break.

Best,

Yang

02.08.2020

Oral Exam Schedule

Dear all,

 

Next week is our PETs oral exam week. The following is the schedule for  each person:

03.08 Monday
    11:00-11:45    Rui Wen
    16:00-16:45    Yongqing Wang
04.08 Tuesday
    10:00-10:45    David Ahmed
    13:00-13:45    Thomas... Read more

Dear all,

 

Next week is our PETs oral exam week. The following is the schedule for  each person:

03.08 Monday
    11:00-11:45    Rui Wen
    16:00-16:45    Yongqing Wang
04.08 Tuesday
    10:00-10:45    David Ahmed
    13:00-13:45    Thomas Boisvert-Bilodeau
05.08 Wednesday
    11:00-11:45    Dominik Kempter
    13:00-13:45    Mejbah Uddin Shameem
    14:00-14:45    Hasan Md Tusfiqur Alam
    15:00-15:45    Rayhanul Islam Rumel
06.08 Thursday
    10:00-10:45    Lin, Yu-De
    11:00-11:45    Omar Mansour
    15:00-15:45    Julian Augustin
    16:00-16:45    Niraj Sorathiya
    17:00-17:45    Dominik Sautter
07.08 Friday
    09:00-09:45    Yugeng Liu
    10:00-10:45    Zubayr Khalid
    11:00-11:45    Barno Kaharova
    13:00-13:45    Maximilian Zöllner
    14:00-14:45    Gayathri Raju Vijayan
    15:00-15:45    Leonard
    16:00-16:45    Jan Cloos
    17:00-17:45    Benjamin Hollinger

 

And here is the zoom link:

Join Zoom Meeting
https://zoom.us/j/94850744633?pwd=QjhSUHoyaU9RS2Yrc251TWlsdzVJdz09

Meeting ID: 948 5074 4633
Passcode: 2e$K*4
One tap mobile
+496950502596,,94850744633# Germany
+496971049922,,94850744633# Germany

Dial by your location
        +49 695 050 2596 Germany
        +49 69 7104 9922 Germany
        +49 30 5679 5800 Germany
Meeting ID: 948 5074 4633
Find your local number: https://zoom.us/u/arlp1gXAR

 

We will choose three of the nine topics which we introduced in the lecture, one topic with detailed questions and two with general questions. Good luck!

 

Cheers,

Min

20.07.2020

Next phase for PETs lecture

Dear all,

 

After checking your first phase code. We decide to let the following students enter the next phase - Oral Exam. 

 

Julian Augustin

Omar Mansour

Gayathri Vijayan

Yu De Lin

David... Read more

Dear all,

 

After checking your first phase code. We decide to let the following students enter the next phase - Oral Exam. 

 

Julian Augustin

Omar Mansour

Gayathri Vijayan

Yu De Lin

David Ahmed

Mejbah Uddin Shameem

Dominik Sautter

Zubayr Khalid

Maximilian Zöllner

Jan Cloos

Dominik Kempter 

Leonard Zitzmann

Barno Kaharova 

Rui Wen

Yugeng Liu

Yongqing Wang

Benjamin Hollinger

Hasan Md Tusfiqur Alam

Rayhanul Islam Rumel

Thomas Boisvert Bilodeau

Niraj Premji Sorathiya

 

Please select a time slot for the oral exam in this doodle link as soon as possible (first come first served). https://doodle.com/poll/exb3bsn8u6a3gqr3

 

Besides, attack three is an essential part of the final score, so, please send the code to me before 12th August.

 

Cheers,

Min

15.07.2020

slides for differential privacy is up

Hi, all

 

Slides for differential privacy is up. Please find it here. https://cms.cispa.saarland/pets2020/materials/

 

Cheers,

Min

 
 
 
 
10.07.2020

Hiwi job from Dr. Giancarlo Pellegrino

Dear all,

Dr. Giancarlo Pellegrino (https://trouge.net/) from CISPA is looking for a HIWI, if you are interested, please contact him directly via email (gpellegrino@cispa.saarland). The advertisement is as follows.

Best,

Yang

Hi all,

I am looking... Read more

Dear all,

Dr. Giancarlo Pellegrino (https://trouge.net/) from CISPA is looking for a HIWI, if you are interested, please contact him directly via email (gpellegrino@cispa.saarland). The advertisement is as follows.

Best,

Yang

Hi all,

I am looking for a very motivated student for a project in my group at the intersection of web security and adversarial machine learning. The success of this project requires the following skills:

1) [required] Knowledge on adversarial machine learning, e.g., generating adversarial examples using Tensorflow (other framework are fine too as long as you know how to migrate models). The interested student should have attended one of the ML and security lectures at UdS (e.g., Machine Learning in Cyber Security by Prof. Fritz) or have self-taught skills on the subject.

2) [optional] Knowledge of browser extensions and independence in reversing Chrome extension JS code also when minified or lightly obfuscated;


Drop me an email if interested and we can schedule a chat and explain the specifics of the project.

Also, feel free to share this message and my email address to other students!

Best,
Giancarlo
02.07.2020

Further Clarification of Semester Project

Hi all,

some of you still have confusion on the semester project. I repeat what I said in the class here.

  • Model Inversion, Algorithm 1 (page 8) in the paper "Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures". Note that... Read more

Hi all,

some of you still have confusion on the semester project. I repeat what I said in the class here.

  • Model Inversion, Algorithm 1 (page 8) in the paper "Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures". Note that AuxTerm(x) = 0, if you are at the class, you should not have this confusion.
  • We recommend you use all these datasets, CIFAR10, MNIST, and Fashion-MNIST.
  • You just need to perform your attack on your local trained model, this means you don't need to attack machine learning models in the cloud.
  • For model extraction/stealing, please check the fourth paragraph of Section 4.1.2 in the paper "Stealing Machine Learning Models via Prediction APIs". That one is designed for MLP, but you can do the same attack on your simple CNN. So in short, just following the methods on my slides is enough.

If you have more questions about the semester project, please contact us by email ASAP. In the next lecture, I'll also be there to answer more questions. If you don't attend most of the lectures, I'm afraid I'm not able to help.

Yang

 

 

01.07.2020

PETs cancelled this week due to the Vodafone Network Disconnection

Dear all,

 

Due to the large scale network disconnection today, we have to cancel the lecture this week. 

We will decide whether to rearrange the missed lecture next week.

 

Cheers,

Min

17.06.2020

chapter 7 slides is up

fyi

10.06.2020

register in lsf

Dear all,

please don't forget to register yourself in LSF.

Yang

10.06.2020

deadline for project phase 1

Dear all,

the deadline for phase 1 of the semester project is July 15th, 2020.

Best,

Yang

03.06.2020

Guides on Attacks Implementation

!--StartFragment--

Dear all,

 

As we mentioned in the seminar, you need to implement three attacks during the seminar, which are Membership Inference Attack, Model Inversion Attack, and Model Stealing Attack(a.k.a Model Extraction Attack).

 

In the... Read more

Dear all,

 

As we mentioned in the seminar, you need to implement three attacks during the seminar, which are Membership Inference Attack, Model Inversion Attack, and Model Stealing Attack(a.k.a Model Extraction Attack).

 

In the first phase, to simplify your tasks and quickly build background knowledge, we have some guides as follows:

  1. You should use a simple convolutional neural network as the basic model for all the three attacks, please refer to the PyTorch tutorial https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html.
  2. We mainly focus on image data and we suggest using the following three datasets: CIFAR10, MNIST, and Fashion-MNIST. You could load the dataset with the python torchvision package, refer to https://pytorch.org/docs/stable/torchvision/datasets.html.
  3. As to the membership inference attack, you only need to implement the "attack one" in the paper titled "ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models".
  4. As to the model inversion attack, you only need to implement the basic model inversion attack in Algorithm 1, refer to the paper titled "Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures".
  5. We will give more information about implementing the model stealing attack next week. You could refer to the paper titled "Stealing Machine Learning Models via Prediction APIs" for some detail in advance.

 

Besides, here is the group information we received so far. I hope no one is missed. :)

1

Julian Augustin,

Mahmoud Fawzi,

Omar Mansour,

Gayathri Vijayan

2

Yu De Lin,

Vikram Vashisth,

David Ahmed,

Mejbah Uddin Shameem,

3

Dominik Sautter

Zubayr Khalid

Maximilian Zöllner

Jan Cloos

4

Dominik Kempter, 

Muhammad Hassan Rashid, 

Leonard Zitzmann,

Barno Kaharova,

5

Rui Wen,

Yugeng Liu,

Yongqing Wang,

Julian Jacques Maurer
6

Benjamin Hollinger

Hasan Md Tusfiqur Alam

Filip Josheski

Rayhanul Islam Rumel

7

Tajbeed Ahmed Chowdhury

Mohammed Raihan Hussain

Thomas Boisvert-Bilodeau

Niraj Premji Sorathiya

 

Best,

Min

27.05.2020

slides for chapter 4 are up

Hi All,

Slides for Chapter 4 are up. Please find it here https://cms.cispa.saarland/pets2020/materials/

 

Thanks,

Ahmed

20.05.2020

Team Building Deadline

Dear all,

 

Today is the deadline for team building. For now, we got 5 teams, the members are as follows.

1

Julian Augustin,

Mahmoud Fawzi,

Omar Mansour,

Gayathri Vijayan

2

Yu De Lin,

... Read more

Dear all,

 

Today is the deadline for team building. For now, we got 5 teams, the members are as follows.

1

Julian Augustin,

Mahmoud Fawzi,

Omar Mansour,

Gayathri Vijayan

2

Yu De Lin,

Vikram Vashisth,

David Ahmed,

Mejbah Uddin Shameem,

3

Dominik Sautter

Zubayr Khalid

Maximilian Zöllner

Jan Cloos

4

Dominik Kempter, 

Muhammad Hassan Rashid, 

Leonard Zitzmann,

Barno Kaharova,

5

Rui Wen,

Yugeng Liu,

Yongqing Wang,

 

If you are not here, please make sure to send your team information to us by the end of today. :)

 

Best,

Min

13.05.2020

slides for chapter 2 are up

please find it here https://cms.cispa.saarland/pets2020/materials/

07.05.2020

Team building forum on google group

Hi, all

I have created a google group for you to build up your team. You may find it by this link, https://groups.google.com/forum/#!managemembers/pets2020.

I have changed some settings, so you could see it without logging in. You need to apply for being a... Read more

Hi, all

I have created a google group for you to build up your team. You may find it by this link, https://groups.google.com/forum/#!managemembers/pets2020.

I have changed some settings, so you could see it without logging in. You need to apply for being a member to see the forum posts, you could log in with any e-mail you could.

If you have any questions, don't hesitate to contact us. 

 

Best,

Min

 
 
 
 
06.05.2020

slides for kick-off and chapter 1 are up

you can find them here

https://cms.cispa.saarland/pets2020/materials/

Cheers,

Yang

30.04.2020

kickoff

Dear all,

the kickoff of our seminar will happen on May 6th, 2020, 12:30-14:00.

Please join via zoom via the following invitation.

Cheers,

Yang

Yang Zhang is inviting you to a scheduled Zoom meeting.

Topic: PETS
Time: This is a recurring meeting... Read more

Dear all,

the kickoff of our seminar will happen on May 6th, 2020, 12:30-14:00.

Please join via zoom via the following invitation.

Cheers,

Yang

Yang Zhang is inviting you to a scheduled Zoom meeting.

Topic: PETS
Time: This is a recurring meeting Meet anytime

Join Zoom Meeting
https://zoom.us/j/93276565793?pwd=UEJWdHdQUWJqUHMvL0VMVWR2MWUzUT09

Meeting ID: 932 7656 5793
Password: 042605
One tap mobile
+496950502596,,93276565793# Germany
+496971049922,,93276565793# Germany

Dial by your location
        +49 695 050 2596 Germany
        +49 69 7104 9922 Germany
        +49 30 5679 5800 Germany
Meeting ID: 932 7656 5793
Find your local number: https://zoom.us/u/abyd3lrKDY

 

Show all
 

Privacy Enhancing Technologies

 

Overview


This course will cover the topic of data privacy from four aspects.

  • Social network privacy
  • Location privacy
  • Machine learning privacy
  • Biomedical privacy

 

Prerequisites


  • Basic knowledge of machine learning and data mining
  • Python
  • Security background is not needed

 

Logistics


Location: Online via Zoom

Lecturers: Yang Zhang

Assistants: Min Chen (min.chen@cispa.saarland), Xinlei He (xinlei.he@cispa.saarland), Ahmed Salem (ahmed.salem@cispa.saarland), Yang Zou (yang.zou@cispa.saarland)

Time: Wednesday 12:30 - 14:00

Contact: Min Chen (min.chen@cispa.saarland)

Office hour: Tuesday, 13:30-16:30; Friday, 13:30-16:30, 3.19 (Please send email for an appointment beforehand!)

 

Schedule


2020.05.06 Social Network Privacy: Attributes Inference
2020.05.13 Social Network Privacy: Graph De-anonymization and New Communication Means
2020.05.20 PyTorch Q&A (Ahmed Salem and Allen He)
2020.05.27 Machine Learning Privacy: Membership Inference (Ahmed Salem)
2020.06.03 Machine Learning Privacy: Machine Learning Privacy: Dataset Reconstruction
2020.06.10 Machine Learning Privacy: Model Stealing
2020.06.17 Machine Learning Privacy: Property Inference and Backdoor
2020.06.24 Location Privacy: Unicity, Attribute Inference, and Location Inference
2020.07.01 Differential Privacy 1 (Zhikun Zhang)
2020.07.08 Differential Privacy 2 (Zhikun Zhang)
2020.07.15 Q&A

Grading


The course will be graded by 50% oral exam and 50% semester project.

 

Exam

 



Privacy Policy | Legal Notice
If you encounter technical problems, please contact the administrators