Data Privacy Yang Zhang

News

21.01.2020

REMINDER: Seminar ended

Dear all,

The seminar ended last Tuesday. There is no class this week.

Thanks a lot for your participation this semester.

Best,

Rui

13.01.2020

Last presentation

Dear all,

 

According to the demands of Darian, we will have only one paper to be presented tomorrow.

14.1.2020

* Anam Sadiq: Exploiting Unintended Feature Leakage in Collaborative Learning

 

Best,

Min

06.01.2020

Latest presentation time and order

Dear all,

Happy new year.

According to the demands of some students, there are some changes in the presentation time and order. Here is the latest.

7.1.2020

* Rui Wen: Latent Backdoor Attacks on Deep Neural Networks

14.1.2020

* Anam Sadiq:... Read more

Dear all,

Happy new year.

According to the demands of some students, there are some changes in the presentation time and order. Here is the latest.

7.1.2020

* Rui Wen: Latent Backdoor Attacks on Deep Neural Networks

14.1.2020

* Anam Sadiq: Exploiting Unintended Feature Leakage in Collaborative Learning

* Darian Hach: Identifying Personal DNA Methylation Profiles by Genotype Inference

Best,

Rui

16.12.2019

Submit the summary report via email

Dear all,

Please submit the summary report via email.

Best,

Rui

03.12.2019

Next week paper changed

Dear all,

There will be a change in the order of the presentations. More concretely, the following presentations are switched:

 

Exploiting Unintended Feature Leakage in Collaborative Learning, It was next week and now will be... Read more

Dear all,

There will be a change in the order of the presentations. More concretely, the following presentations are switched:

 

Exploiting Unintended Feature Leakage in Collaborative Learning, It was next week and now will be on 7.1.2020.

 

Characterizing and Detecting Malicious Accounts inPrivacy-Centric Mobile Social Networks: A Case Study, It was on 7.1.2020 and it will be next week.

 

 

Thanks,

Ahmed

 
 
28.11.2019

About the final summary

Dear all,

The final summary of all presentations needs to be 2 - 3 pages.

Best,

Rui

26.11.2019

Organizational news

Dear All,

 

As we discussed today after the seminar.

1- The presentation time should not exceed 30 minutes.

2- You can pick only one paper to ask questions about, but the questions/comments need to be meaningful!.

3- The seminar starts at 12:15 and... Read more

Dear All,

 

As we discussed today after the seminar.

1- The presentation time should not exceed 30 minutes.

2- You can pick only one paper to ask questions about, but the questions/comments need to be meaningful!.

3- The seminar starts at 12:15 and ends at 14:15.

 

Thanks,

Ahmed

08.11.2019

Presentation date and order

Dear all,

Here are the presentation date and order.

19.11.2019

* Sabine Houy: Privacy-Preserving Crowd-Sourcing of Web Searches with Private Data

26.11.2019

* Nicolas Tran: Auditing Data Provenance in Text-Generation Models

* Rayhanul Islam Rumel:... Read more

Dear all,

Here are the presentation date and order.

19.11.2019

* Sabine Houy: Privacy-Preserving Crowd-Sourcing of Web Searches with Private Data

26.11.2019

* Nicolas Tran: Auditing Data Provenance in Text-Generation Models

* Rayhanul Islam Rumel: PrivIdEx: Privacy Preserving and Secure Exchange of Digital Identity Assets.

3.12.2019

* Wentao Liu: MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples

* Pradeep Karki: Detecting Fake Accounts in Online Social Networks at the Time of Registrations

10.12.2019

* Anam Sadiq: Exploiting Unintended Feature Leakage in Collaborative Learning

* Lukas Schmitz: Knockoff Nets: Stealing Functionality of Black-Box Models

17.12.2019

* Darian Hach: Identifying Personal DNA Methylation Profiles by Genotype Inference

* Yugeng Liu: Privacy Risks of Securing Machine Learning Models against Adversarial Examples

7.1.2020

* Rui Wen: Latent Backdoor Attacks on Deep Neural Networks

Best wishes,

Rui

04.11.2019

Paper Assignment

Dear all,

 

Here is the paper assignment:

Alaeddine Abroug: Characterizing and Detecting Malicious Accounts inPrivacy-Centric Mobile Social Networks: A Case Study

Pradeep Karki: Detecting Fake Accounts in Online Social Networks at the... Read more

Dear all,

 

Here is the paper assignment:

Alaeddine Abroug: Characterizing and Detecting Malicious Accounts inPrivacy-Centric Mobile Social Networks: A Case Study

Pradeep Karki: Detecting Fake Accounts in Online Social Networks at the Time of Registrations

Rui Wen: Latent Backdoor Attacks on Deep Neural Networks

Wentao Liu: MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples

Sabine Houy: Privacy-Preserving Crowd-Sourcing of Web Searches with Private Data

Nicolas Tran: Auditing Data Provenance in Text-Generation Models

Thanks,
Ahmed
 
 

 
 

 

31.10.2019

REMINDER: Deadline to pick papers

Dear all,

Please send your email with 3 picked papers before next Monday.

Best wishes,

Rui

29.10.2019

kickoff slides

Dear all, 

the kickoff slides can be found in https://cms.cispa.saarland/dp2019/materials/

Cheers,

Yang

29.10.2019

Papers for pick

Dear all,

13 papers for presentations are listed on https://cms.cispa.saarland/dp2019/. Please check it and send us an email with your picked 3 papers.

Best wishes,

Rui

Show all
 

Data Privacy

The development of ICT has resulted in an unprecedented amount of data available. The big data, on the one hand, bring many benefits to society, on the other hand, raises serious concerns about people's privacy. In this seminar, students will learn, summarize, and present state-of-the-art scientific papers in data privacy. Topics include social network privacy, machine learning privacy, and biomedical data privacy. The seminar is organized as a reading group. Every week, one student will present her/his assigned papers on a certain topic, followed by a group discussion. All students are required to read the papers carefully and prepare a list of questions for discussion. Each student will write a summary of her/his assigned papers providing a general overview of the field.

 

Logistics

Time: Tuesday 12:00-14:00

Venue: 0.06, E9 1

 

Instructors

Yang Zhang (zhang@cispa.saarland)

Min Chen (min.chen@cispa.saarland)

Ahmed Salem (ahmed.salem@cispa.saarland)

Rui Ye (rui.ye@cispa.saarland)

 

Papers

1 "Exploiting Unintended Feature Leakage in Collaborative Learning" https://arxiv.org/abs/1805.04049

2 "MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples" https://arxiv.org/abs/1909.10594

3 "Auditing Data Provenance in Text-Generation Models" https://arxiv.org/abs/1811.00513

4 "Privacy Risks of Securing Machine Learning Models against Adversarial Examples" https://arxiv.org/abs/1905.10291

5 "Knockoff Nets: Stealing Functionality of Black-Box Models" https://arxiv.org/abs/1812.02766

6 "Latent Backdoor Attacks on Deep Neural Networks" http://people.cs.uchicago.edu/~ravenben/publications/pdf/pbackdoor-ccs19.pdf

7 “Identifying Personal DNA Methylation Profiles by Genotype Inference” https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7958619

8 “P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification” https://arxiv.org/abs/1905.12883

9 “MBeacon: Privacy-Preserving Beacons for DNA Methylation Data” https://www.ndss-symposium.org/wp-content/uploads/2019/02/ndss2019_03A-2_Hagestedt_paper.pdf

10 “Characterizing and Detecting Malicious Accounts inPrivacy-Centric Mobile Social Networks: A Case Study” https://www.kdd.org/kdd2019/accepted-papers/view/characterizing-and-detecting-malicious-accounts-inprivacy-centric-mobile-so

11“Privacy-Preserving Crowd-Sourcing of Web Searches with Private Data Donor” https://emilianodc.com/PAPERS/pdd-www19.pdf

12 “PrivIdEx: Privacy Preserving and Secure Exchange of Digital Identity Assets.” https://dl.acm.org/citation.cfm?doid=3308558.3313574

13 “Detecting Fake Accounts in Online Social Networks at the Time of Registrations” http://people.duke.edu/~zg70/papers/Ianus.pdf

1-6 Machine learning privacy, 7-9 Health privacy, 10-13 Social network privacy

 



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