News

seminar next week

Written on 09.01.19 by Yang Zhang

Hi,

my last email was not clear enough, there will be a seminar next week!

Cheers,

Yang 

presentation cancelled tomorrow

Written on 07.01.19 by Yang Zhang

Dear all,

as the speaker for tomorrow can't make it, let's cancel our class tomorrow!

Cheers,

Yang

room change on Dec. 11

Written on 28.11.18 by Yang Zhang

Dear all,

we will use room 0.06 on Dec. 11th.

Many thanks!

Yang

Data Privacy

 

The development of ICT has resulted in an unprecedented amount of data available. The big data, on one hand, bring many benefits to the 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 12:30-14:00

Venue: 0.07, E9 1

Instructors

Yang Zhang (yang.zhang@cispa.saarland)

Inken Hagestedt (inken.hagestedt@cispa.saarland)

Ahmed Salem (ahmed.salem@cispa.saarland)

Papers

  1. Identifying Personal DNA Methylation Profiles by Genotype Inference
  2. Privacy Risks from Genomic Data-Sharing Beacons
  3. GenoShare: Supporting Privacy-Informed Decisions for Sharing Exact Genomic Data
  4. Identifying personal microbiomes using metagenomic codes
  5. Membership Inference Attacks Against Machine Learning Models
  6. Towards Reverse-Engineering Black-Box Neural Networks
  7. Machine Learning Models that Remember Too Much
  8. Stealing Machine Learning Models via Prediction APIs
  9. Analysis of Privacy Protections in Fitness Tracking Social Networks -or- You can run, but can you hide?
  10. Privacy Risks with Facebook's PII-based Targeting: Auditing a Data Broker's Advertising Interface
  11. AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning

1-4 Health privacy, 5-8 Machine learning privacy, 9-11 Social network privacy

 

Paper Assignment

Each student chooses 3 papers and sends them to Yang Zhang (yang.zhang@cispa.saarland) by October 28th, 2018.

The assignment will be done by October 30th, 2018.

The first seminar starts on November 6th, 2018!

 

Style

  • Each student will present her/his paper for 30 minutes followed by a group discussion.
  • Each audience is required to ask at least 2 questions.
  • After the presentation, the student will submit a report within 3 weeks.

All the above three items are graded.

Besides, each student can have a maximal 30 minutes discussion with one of the instructors before her/his presentation, this part will not be graded.

 

 

 

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