The Cybersecurity Crisis of Artificial Intelligence: Unrestrained Adoption and Natural Language-Based Attacks

11 Pages Posted: 21 Sep 2023 Last revised: 6 Nov 2023

See all articles by Andreas Tsamados

Andreas Tsamados

University of Oxford, Oxford Internet Institute

Luciano Floridi

Yale University - Digital Ethics Center; University of Bologna- Department of Legal Studies

Mariarosaria Taddeo

University of Oxford - Oxford Internet Institute

Date Written: September 20, 2023

Abstract

The widespread integration of autoregressive-large language models (AR-LLMs), such as ChatGPT, across established applications, like search engines, has introduced critical vulnerabilities with uniquely scalable characteristics. In this article, we analyse these vulnerabilities, their dependence on natural language as a vector of attack, and their challenges to cybersecurity best practices. We offer recommendations designed to mitigate these challenges.

Keywords: Artificial Intelligence, Autoregressive-Large Language Models, Cybersecurity, Adversarial Examples, Natural Language

Suggested Citation

Tsamados, Andreas and Floridi, Luciano and Taddeo, Mariarosaria, The Cybersecurity Crisis of Artificial Intelligence: Unrestrained Adoption and Natural Language-Based Attacks (September 20, 2023). Available at SSRN: https://ssrn.com/abstract=4578165 or http://dx.doi.org/10.2139/ssrn.4578165

Andreas Tsamados

University of Oxford, Oxford Internet Institute ( email )

1 St. Giles
University of Oxford
Oxford OX1 3PG Oxfordshire, Oxfordshire OX1 3JS
United Kingdom

Luciano Floridi

Yale University - Digital Ethics Center ( email )

85 Trumbull Street
New Haven, CT CT 06511
United States
2034326473 (Phone)

University of Bologna- Department of Legal Studies ( email )

Via Zamboni 22
Bologna, Bo 40100
Italy

HOME PAGE: http://www.unibo.it/sitoweb/luciano.floridi/en

Mariarosaria Taddeo (Contact Author)

University of Oxford - Oxford Internet Institute ( email )

1 St. Giles
University of Oxford
Oxford OX1 3PG Oxfordshire, Oxfordshire OX1 3JS
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1,140
Abstract Views
4,491
Rank
37,666
PlumX Metrics