Develop robust algorithms capable of handling security threats to federated learning scenarios.
About this Event
Date And Time
Tue, Nov 24, 2020, 10:00 AM – Wed, Nov 25, 2020, 5:00 PM CET
You’ll have the opportunity to develop robust algorithms capable of handling security threats to federated learning scenarios where malicious users try to compromise your machine learning model. The algorithms will be implemented in Python using the Keras Deep Learning framework, and be executed among remote participants via the MUSKETEER cloud platform for federated learning. The event will take place in different locations at the same time around Europe. Join us in Berlin, Dublin or Palermo for this day of intensive test and discussions about advanced privacy preserving technologies.
COVID-19 Update: the current crisis does not allow us to properly welcome the participants in a physical meeting. Therefore, this hackathon will be 100% online. We know the importance of meeting in person, especially for such a format of event. Therefore, we’ll do our best to organize and foster interaction among participants during the two days.
Agenda
1st Day: November 24, 2020 (All times are GMT)
9:00-9:15 – Hackathon welcome note
9:15-10:00 – Technical Talk: Introduction to Federated Learning and MUSKETEER
10:00-10:45 – Hackathon rules, guidelines, general instructions, Q&A
10:45-11:00 – Break
11:00-13:00 – [Breakout rooms] Hacking phase I
13:00-13:45 – Lunch break
13:45-16:00 – Hacking phase 2
16:00-16:30 – Day 1 debrief
2nd day: November 25, 2020 (All times are GMT)
9:00-9:15 – Recap from Day 1 and outlook on the day
9:15-13:00 – Hacking Phase 3
13:00-14:00 – Lunch break
14:00-14:30 – Technical talk on robustness of federated machine learning
14:30-15:00 – Attack Scenarios used in the Hackathon
15:00-15:30 – Assembly, winner ceremony, virtual group photo, and closing remarks
Minimum skills
- Solid Python 3 programming skills, experience with training simple classifier models in Keras, basic understanding of federated learning
- Familiarity with federated learning will be ideal.
- Participants are required to bring their own laptop
Organizers
MUSKETEER aims to develop an industrial data platform with scalable algorithms for federated and privacy-preserving machine learning techniques, detection and mitigation of model capable of fairly monetizing datasets according to their real data value. MUSKETEER is an H2020 project that has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 824988.
