Skip to content

it-7th/FL_Privacy

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FL-PETS

Privacy Enhancing Technologies in Federated Learning

Simulation framework for evaluating privacy attacks and defenses in Federated Learning, with a focus on Differential Privacy (DP) and Secure Multi-Party Computation (SMPC).

Developed as part of the Cyber Lab 1 course at Eötvös Loránd University (ELTE).


Project Overview

FL-PETS is a Federated Learning (FL) simulation framework designed to benchmark various Privacy Enhancing Technologies (PETs) against common adversarial attacks. The framework evaluates privacy–utility trade-offs under realistic threat models.


Privacy Defenses Implemented

  • Differential Privacy (DP)
    Statistical noise injection using Opacus.

  • Homomorphic Encryption (HE)
    Encrypted aggregation using TenSEAL (CKKS scheme).

  • Secure Multi-Party Computation (SMPC)
    Cryptographic secret sharing for secure aggregation.

  • Hybrid (DP + SMPC)
    Defense-in-depth approach combining statistical and cryptographic protections.


Attacks Evaluated

  • Gradient Inversion (Training Data Reconstruction)
  • Membership Inference Attack (MIA)
  • Model Extraction (Functionality Stealing)

Getting Started

Install Dependencies

pip install -r requirements.txt

Run Full Experimental Sweep

./run_experiments.sh

This script executes all defense–attack combinations and collects evaluation metrics.


Experimental Results

The project analyzes the trade-off between model utility (accuracy) and privacy guarantees.

Example findings:

  • Baseline FL reaches 96.90% accuracy but is highly vulnerable to attacks.
  • Hybrid (DP + SMPC) provides maximum resistance to Model Extraction, at the cost of reduced utility (75.62% accuracy).

Research Focus

This project is intended for:

  • Privacy-preserving machine learning research
  • Federated learning security evaluation
  • Benchmarking PETs under adversarial threat models

License

This project is licensed under the MIT License - see the LICENSE file for details.

About

Simulation framework for evaluating privacy attacks and defenses in Federated Learning — focusing on Differential Privacy (DP) and Secure Multi-Party Computation (SMPC). Developed as part of the Cyber Lab 1 course at Eötvös Loránd University (ELTE).

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors