Skip to content

Repository files navigation

Data Poisoning Attacks

Abstract

This repository presents an academic study of data poisoning attacks in machine learning systems.
The research investigates training-time adversarial manipulations, their formal threat models, practical implementation, and impact on the security and robustness of machine learning models.


Index Terms

Data Poisoning Attacks, Adversarial Machine Learning, Machine Learning Security, Training-Time Attacks, Model Robustness.


Research Objectives

The objectives of this research are:

  • to formally define data poisoning attacks and their threat models;
  • to analyze existing attack strategies and taxonomies;
  • to evaluate the effect of poisoned training data on model performance;
  • to reproduce selected poisoning attacks through controlled experiments;
  • to review and compare existing defense and mitigation techniques.

Scope

This research focuses on:

  • supervised learning under adversarial training conditions;
  • label-flipping and clean-label poisoning attacks;
  • targeted and untargeted poisoning scenarios;
  • backdoor injection during the training phase;
  • security evaluation and robustness analysis of machine learning models.

Authors

  • Mikhail Shumakov
  • Arseniy Shchekin

About

Research repository dedicated to the study of Data Poisoning Attacks. Contains academic references and practical experiments illustrating key concepts and methods. Authors: Mikhail Shumakov, Arseniy Shchekin

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors