Date of Award

Fall 1-15-2023

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Margaret McCoey

Language

ENGLISH

Abstract

Artificial Intelligence (AI) adoption is rapidly being deployed in a number of fields, from banking and finance to healthcare, robotics, transportation, military, e-commerce and social networks. Grand View Research estimates that the global AI market was worth 93.5 billion in 2021 and that it will increase at a compound annual growth rate (CAGR) of 38.1% from 2022 to 2030. According to a 2020 MIT Sloan Management survey, 87% of multinational corporations believe that AI technology will provide a competitive edge. Artificial Intelligence relies heavily on datasets to train its models. The more data, the better it learns and predicts. However, the downside to AI is data, data that can be manipulated or poisoned. A new type of threat is emerging, and that threat is data poisoning. Data Poisoning is challenging and time consuming to spot and when it is discovered, the damage is already extensive. Unlike traditional attack that is caused by errors found in code, this new threat is attacking the AI training data used in its algorithm. Data is now being weaponized. It requires minimal effort but can cause substantial damages. It only takes 1-3% of data to be poisoned to severely diminish an AI’s ability to produce accurate predictions.

Download

Share

COinS