AIJack: Let's Hijack AI! Security and Privacy Risk Simulator for Machine Learning

TL;DR

AIJack is an open-source toolkit that simulates security and privacy risks in machine learning, helping researchers and practitioners evaluate vulnerabilities and defenses in ML systems.

Contribution

It provides a unified API with diverse attack and defense methods, facilitating comprehensive security and privacy risk assessment for ML models.

Findings

Enables simulation of various attack scenarios on ML models

Supports evaluation of defense strategies against security threats

Open-source availability encourages community-driven improvements

Abstract

This paper introduces AIJack, an open-source library designed to assess security and privacy risks associated with the training and deployment of machine learning models. Amid the growing interest in big data and AI, advancements in machine learning research and business are accelerating. However, recent studies reveal potential threats, such as the theft of training data and the manipulation of models by malicious attackers. Therefore, a comprehensive understanding of machine learning's security and privacy vulnerabilities is crucial for the safe integration of machine learning into real-world products. AIJack aims to address this need by providing a library with various attack and defense methods through a unified API. The library is publicly available on GitHub (https://github.com/Koukyosyumei/AIJack).