Download This PaperThe Cybersecurity Crisis of Artificial Intelligence: Unrestrained Adoption and Natural Language-Based Attacks
11 Pages Posted: 21 Sep 2023 Last revised: 6 Nov 2023
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: 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
Do you have a job opening that you would like to promote on SSRN?
Feedback
Feedback to SSRN
If you need immediate assistance, call 877-SSRNHelp (877 777 6435) in the United States, or +1 212 448 2500 outside of the United States, 8:30AM to 6:00PM U.S. Eastern, Monday - Friday.