Federated Learning (FL) is a decentralized approach to machine learning that allows multiple participants to collaboratively train a model without sharing their raw data. This approach ensures privacy by keeping data local while enabling insights to be gained from distributed datasets. However, traditional implementations of FL face several challenges, including limited scalability, inefficiency, and vulnerabilities to cyberattacks. Recent research highlights that due to FL's distributed nature, the effects of cyberattacks seen in centralized model training cannot be directly applied to federated model training, requiring a re-evaluation of the threat landscape.
This workshop will introduce FEDn, a framework specifically designed to overcome the scalability, efficiency, and security challenges of federated learning. We will explore how FEDn supports both cross-device and cross-silo use cases, making it a versatile solution for diverse scenarios. Additionally, we will discuss ongoing work into understanding cyberattack impacts in FL and strategies for mitigating these threats.
The workshop will include a hands-on session, where participants will collaboratively train a machine learning model using FEDn Studio, providing practical insights into the framework's capabilities.
This workshop is designed for a diverse audience interested in exploring the cutting-edge advancements in federated learning and its practical applications. It is ideal for:
Business Leaders: Gain high-level insights into how federated learning can drive innovation while preserving data privacy and security.
Product Owners: Understand the opportunities and challenges of integrating federated learning into your product roadmap.
Technology Experts: Explore the technical depth of FEDn and its potential to address real-world scalability and security concerns.
Tech Enthusiasts: Engage with hands-on learning, ideal for DevOps professionals, data engineers, and machine learning experts looking to expand their skill set in decentralized AI.
Whether you are a decision-maker aiming to adopt privacy-preserving AI solutions or a technical professional interested in federated learning's practical aspects, this workshop offers valuable knowledge and actionable insights tailored to your interests.
Salman Toor: Associate Professor in Scientific Computing at Uppsala University and the co-founder and CTO of Scaleout Systems. He is an expert in distributed computing infrastructures and applied machine learning. Toor is also one of the lead architects of the FEDn framework, which was designed and developed to enable scalable federated machine learning.
Viktor Valadi: Machine Learning Engineer at Scaleout, Masters at Chalmers University in Computer Science, Gothenburg, Sweden. Background in Federated Learning Cyber Security research relating to both privacy and robustness.
Introductory level understanding of neural networks.
