Skip to content
Back to all projects
  • Machine Learning
  • Cybersecurity

FL-AHPS: Federated Learning-Based Account Hijack Prevention

A privacy-preserving authentication system that detects account hijacking from contextual login behavior.

Overview

Login context — IP, device fingerprint, browser, location and time — is analysed for anomalies, with detection models trained across devices through federated learning so raw user data never leaves the client. SVM and Logistic Regression assign each login a risk level, and Zero Trust adaptive authentication enforces context-aware challenges based on that risk.

Problem Statement

Stolen credentials defeat password authentication entirely, and the behavioural data needed to spot a hijacked login is exactly the data users least want centralised on a server.

Proposed Solution

Train the anomaly detection models federated across devices so raw login context stays local, and use the resulting risk score to drive Zero Trust adaptive challenges rather than a fixed rule.

Key Features

  • Contextual Anomaly Detection

    Analyzes IP, device fingerprint, browser, location, and login time.

  • Federated Learning

    Trains detection models across devices without sharing raw user data.

  • Risk-Scored Login Classification

    SVM and Logistic Regression assign a login risk level.

  • Zero Trust Adaptive Authentication

    Enforces context-aware security challenges based on risk.

Technologies Used

Machine Learning

  • SVM
  • Logistic Regression
  • Federated learning
  • Scikit-Learn

Security

  • Device fingerprinting
  • Zero Trust
  • Adaptive MFA

Application

  • Flask / FastAPI
  • PostgreSQL
  • React

Project Workflow

  1. 1

    Context capture

    IP, device, browser, location and time are collected at login.

  2. 2

    Local training

    Models train on-device without exporting raw data.

  3. 3

    Federated aggregation

    Model updates are aggregated centrally.

  4. 4

    Risk scoring

    Each login attempt is assigned a risk level.

  5. 5

    Adaptive challenge

    Zero Trust rules enforce challenges proportional to risk.

What You'll Receive

  • Complete, runnable source code with folder structure
  • Project report and technical documentation
  • Ready-to-present PPT content
  • Setup and installation walkthrough
  • Line-by-line project explanation session
  • Viva question bank with answers
  • Bug fixing and troubleshooting help
  • Post-delivery support after submission

Frequently Asked Questions

How much does this project cost?

Every project is quoted individually, because the price depends on the modules you need, your technology stack, your college's format and your deadline. Send us the project name on WhatsApp and we'll share a quote the same day.

Can the project be customised to my college requirements?

Yes. Share your guide's requirements, preferred technology stack and abstract format, and we adapt the modules, dataset or UI accordingly.

Will I be able to explain this project during my viva?

That is the point of the explanation session. We walk you through the architecture, every module, the flow of data and the results, and hand over a viva question bank with answers.

What if the project does not run on my laptop?

We help you with setup end to end — dependencies, environment, database and configuration — over chat or a call until it runs on your machine.

Do I get support after submission?

Yes. Post-delivery support is included, so you can come back for fixes, doubts or demo help even after the project is delivered.

Want This Project?

Get complete source code, documentation, PPT, explanation, and support.

Similar projects

  • Machine Learning

Business Analytics Platform

A web-based analytics platform that helps businesses analyze historical data and make informed decisions.

  • Customer Churn Analyzer
  • Sales Forecasting
  • Customer Segmentation
  • +1 more

Custom quote

Priced to your scope

View Project