HIDA Summer exchange

DSRC@BGU - HIDA summer exchange program

Would you like to spark collaborations with data scientists in Israel, learn, work on exciting projects and publish together? Then apply to the Helmholtz Information and Data Science Academy’s (HIDA) exchange program with the Data Science Research Center at Ben-Gurion University of the Negev (DSRC@BGU) in Be’er Sheva Israel.

About the exchange program

  • You spend your exchange at a host lab at Ben Gurion University. Depending on travel restrictions, you can also start the collaboration remotely and complete your project onsite in Be’er Sheva.
  • You apply to and work on a pre-defined six-week-long project of your choice (please list see below) together with data scientists at BGU.
  • HIDA covers your accommodation and travel expenses (up to 2000 Euro per month) if you work for a Helmholtz Center.

The logistics

  • The closing date for applications was June 19, 2020.
  • Earliest start-date for the (physical) exchange is July 1; latest end date is December 31. You and your host decide which part of the project you might be able to work on remotely, and when you’ll spend time collaborating at BGU.
  • You organize your trip to and accommodation in Be’er Sheva as a business trip. HIDA will reimburse your Helmholtz Center.

You can apply to the following projects for our summer 2020 exchange

[Translate to Englisch:] Photo: ZU photography / Unsplash

Project 1: Accuracy of attack hypotheses in telemetry data

Host

Rami Puzis

Department

Software and information systems engineering

Link to group/lab

https://faramirp.wixsite.com/puzis

Three-sentence summary of the group's research

At Complex Networks Analysis Lab at Ben-Gurion University (CNALAB@BGU) we tackle research problems in diverse domains using a combination of methods from graph theory and machine learning. Complex Networks are found in cyber security, social networks, communication networks and the Internet, biological networks, financial networks, text analytics and more. Scientific programmers working the CNA Lab @ BGU develop generic software tools and libraries to analyze the structure of networks derived from the various problem domains. Graduate research students apply these tools to investigate specific problems in their domain of interest.

What is the data science project's research question?

How does the accuracy of artifacts detection affect the accuracy of attack hypotheses generated from telemetry data?

What data will be worked on?

A knowledge base consisting of merged threat intelligence sources

What tasks will this project involve? 

Implementing several attack hypothesis generation methods. Implementing an evaluation pipeline. Experimenting with different FPR FNR at the level of artifact detection. Analyzing the accuracy of hypotheses at the level of MITRE ATT&CK techniques.

What makes this project interesting to work on? 

Under-explored domain of threat hunting. Unique knowledge base. Variety of methods (graph theoretic, information retrieval, machine learning, ...) applicable to the problem. Room for self-expression.

What is the expected outcome?

Contribution to research paper

Is the data open source?

No

What infrastructure, programs and tools will be used?

Python, neo4j, graph and machine learning libraries

What skills are necessary for this project?

Scientific computation, Data mining / Machine learning, Basic Graph theory

What level of experience is necessary for this project?

Master level

How many people may be hosted for this project?

2

Would the participant be working as part of a team or individually?

Team

Read more about Rami’s lab and working with him! 

[Translate to Englisch:] Photo: Roman Kraft / Unsplash

Project 2: Detecting fake news

Host

Rami Puzis

Department

Software and information systems engineering

Link to group/lab

https://faramirp.wixsite.com/puzis

Three-sentence summary of the group's research

At Complex Networks Analysis Lab at Ben-Gurion University (CNALAB@BGU) we tackle research problems in diverse domains using a combination of methods from graph theory and machine learning. Complex Networks are found in cyber security, social networks, communication networks and the Internet, biological networks, financial networks, text analytics and more. Scientific programmers working the CNA Lab @ BGU develop generic software tools and libraries to analyze the structure of networks derived from the various problem domains. Graduate research students apply these tools to investigate specific problems in their domain of interest.

What is the data science project's research question?

Detecting fake news

What data will be worked on?

A large-scale dataset with millions of tweets related to 70K fake and real news items.

What tasks will this project involve? 

Development of machine learning classifiers to take false and true news apart based on the public feedback on Twitter. The research may involve account classification as well. The research may involve generation of a small-scale dataset of stance toward a news items to be used for fake news analysis using stance detection.

What makes this project interesting to work on? 

Large-scale real dataset. Variety of techniques that can be used to solve the problem. Possibility for affecting the research approach.

What is the expected outcome?

Contribution to research paper. Contribution to software development

Is the data open source?

Not yet

What infrastructure, programs and tools will be used?

Server, python, scientific libraries. Possibly HPC.

What skills are necessary for this project?

Data analytics / statistics, Scientific computation, Data mining / Machine learning

What level of experience is necessary for this project?

Master level

How many people may be hosted for this project?

2

Would the participant be working as part of a team or individually?

Team

[Translate to Englisch:] Photo: Rodion Kutsaev / Unsplash

Project 3: Preventing attacks on smartphone sensors

Host

Yossi Oren

Department

Software and Information Systems Engineering

Link to group/lab

https://orenlab.sise.bgu.ac.il

Three-sentence summary the group's research

We will be happy to host you at the Oren Lab, where we study Implementation Security and side-channel attacks at Ben-Gurion University, Israel. This particular project is related to attacks and defenses on smartphone sensors.

What is the data science project's research question? 

Can we use machine learning to implement OS-level defenses from attacks on smartphone sensors?

What data will be worked on? 

Timestamped events of sensors during multiple user activities, previously collected through an IRB-controlled user study.

What tasks will this project involve? 

Training a model for a time-series, finding good pre-processing methods, testing the model on multiple datasets, evaluating real-time performance, participating in the technical writing effort.

What makes this project interesting to work on? 

If successful, this project can result in a first-of-its-kind defense from sensor attacks that will be integrated in real-time on mobile devices.

What is the expected outcome? 

Contribution to research paper. Contribution to software development

Is the data open source? 

Yes

What infrastructure, programs and tools will be used? 

Tensor flow lite, python, Matlab

What skills are necessary for this project? 

Data analytics / statistics, Data mining / Machine learning, Deep learning, Scientific Writing

What level of experience is necessary for this project? 

Phd-level

How many people may be hosted for this project? 

1

Would the participant be working as part of a team or individually? 

Team

About the Data Science Research Center at Ben-Gurion University

The Data Science Research Center (DSRC@BGU) was founded in 2018 as a central hub of education and research at Ben-Gurion University of the Negev. DSRC@BGU, with its over 70 members, offers concentrated expertise in all aspects of data science, in application and research as well as in education. The center’s members research and teach at many institutes at BGU, bridging domains and data science. At the center, they work on theoretical and practical problems in data mining, machine learning, and big data along with applying data science methods and tools to such diverse fields as natural language processing, artificial intelligence, bioinformatics, computational biology, computer vision, medical diagnostics, precision agriculture, robotics, and many others.

About the Helmholtz Information & Data Science Academy

HIDA – The Helmholtz Information & Data Science Academy – is Germany’s largest postgraduate training network in information and data science. We prepare the next generation of scientists for a data-heavy future of research. HIDA connects and serves as the roof to 6 newly founded data science research schools linked by a network of 14 national research centers and 17 top-tier universities across Germany. During the next 5 years, these data science research schools will train over 250 fully funded doctoral researchers. The doctoral researchers will deepen their knowledge in data science methods and learn to combine knowledge from the six Helmholtz research areas – energy, earth and environment, health, aeronautics, space and transport, matter, and information – with data science methods. For these purposes, all doctoral researchers receive dual supervision in data science and their scientific domain. In addition, HIDA offers doctoral researchers and scientists attractive opportunities to obtain training and continuing education in a wide range of methods and to become part of an international data science network.

Do you have questions about the application process or program?

Please get in touch: hida@helmholtz.de

We are looking forward to hearing from you!

download