Skip to content

Repository files navigation

FENIX Project

Federated Learning Security and Evaluation Framework for Foundation Models


Overview

FENIX is a research project developed during the Industrial Immersion Program at AI Sweden.

The project focused on evaluating and improving the robustness of large language models (LLMs) in federated learning environments, with a particular emphasis on:

  • Foundation model evaluation
  • Federated learning workflows
  • Data poisoning attacks
  • Model poisoning attacks
  • Security and robustness analysis
  • Benchmark development

The primary model used in the project was GPT-SW3, one of Sweden's large language models.


Motivation

As large language models become increasingly distributed across organizations and infrastructure environments, federated learning introduces new opportunities and challenges.

While federated training can improve privacy and collaboration, it also introduces additional attack surfaces:

  • Malicious client updates
  • Data poisoning
  • Model poisoning
  • Evaluation inconsistencies

This project explored how these risks affect foundation models and how benchmarking frameworks can be used to identify weaknesses and improve reliability.


Research Areas

Federated Learning

Implemented and evaluated federated learning workflows for foundation models.

Topics explored:

  • Distributed training environments
  • Client-server update aggregation
  • Model synchronization
  • Federated evaluation pipelines

Foundation Model Evaluation

Developed benchmarking workflows for GPT-SW3-based systems.

Objectives:

  • Measure model performance
  • Compare evaluation results across training scenarios
  • Improve reproducibility of benchmark results

Security Analysis

Conducted simulations of adversarial attacks against federated learning systems.

Attack scenarios included:

  • Data poisoning
  • Model poisoning
  • Malicious update injection

The goal was to identify vulnerabilities and better understand failure modes in distributed AI systems.


Project Structure

Fed_simple/
Fed_simple_MP/
Fed_LoRA/
Fed_LoRA_MP/

training_federated_full.py
prompt_generation.py

Core areas:

  • Federated training workflows
  • LoRA-based fine-tuning experiments
  • Prompt generation
  • Benchmark evaluation

Key Learning Outcomes

Through this project, I gained practical experience with:

  • Federated Learning
  • Foundation Models
  • GPT-SW3
  • Distributed AI Systems
  • AI Security Research
  • Benchmark Development
  • Model Evaluation Methodologies

Related Experience

This project was conducted as part of the AI Sweden Industrial Immersion Program in collaboration with Dakota State University.

The research contributed to:

  • Foundation model benchmarking
  • Security evaluation of federated learning systems
  • Robustness analysis for distributed AI environments

Technologies

  • Python
  • GPT-SW3
  • Federated Learning
  • LoRA
  • Machine Learning Evaluation Pipelines

Project Goal

The long-term objective of FENIX is to better understand how foundation models behave in distributed environments and how security-focused evaluation frameworks can improve the reliability of future AI systems.

About

Repo for the Foundation project at A.I Sweden

Resources

Stars

1 star

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages