Skip to content

scatter_plot InteFL

Federated learning execution & research framework

shield 9 Strategies | bug_report 11 Attacks | database 20+ Datasets

What Is InteFL?

InteFL is a full-stack federated learning platform for running, attacking, and defending distributed ML simulations. Configure a JSON file, launch a simulation, and get CSV metrics, PDF plots, and attack snapshot reports — all orchestrated through a React dashboard or CLI.

Configure. Simulate. Analyse.

Define your experiment in a single JSON config. InteFL handles dataset partitioning, client orchestration, adversarial injection, and results collection. Compare strategies side-by-side. Reproduce every run.
Research-grade reproducibility, out of the box.

One Config, Full Pipeline

data_object Config
play_circle Runner
scatter_plot Simulation
shield Strategy
group Clients
trending_up Results

JSON config → partitioned datasets → N federated clients → aggregated metrics, plots, and snapshots

Key Features

verified_user 9 Aggregation Strategies

FedAvg, Krum, Multi-Krum, Bulyan, RFA, Trimmed Mean, PID-based, Trust-based, ArKrum — each with configurable parameters

warning 11 Attack Types

Data poisoning: label flipping, targeted label flipping, Gaussian noise, backdoor triggers, token replacement
Model poisoning: model poisoning, gradient scaling, boosted scaling, Byzantine perturbation, inner product manipulation, alternating min

photo_library Rich Dataset Support

FEMNIST, FLAIR, CIFAR-100, 11 MedMNIST subsets, Lung Cancer, plus HuggingFace text datasets (financial, legal, medical)

layers Full-Stack Platform

REST API + React dashboard, Celery task queue, SSE live streaming, Docker Compose deployment, and this docs site — all included

Technology Stack

psychology FL Flower (flwr)
bolt Compute Ray
local_fire_department DL PyTorch
smart_toy LLM HuggingFace + PEFT
api API FastAPI + Uvicorn
inbox Queue Celery + Redis
code UI React + Vite
menu_book Docs Zensical

Ready to Simulate?

Configure. Launch. Defend. Analyse.

Get Started
AJ Barea · 2026