Analysis

How to Assess the Likelihood of Malicious Use of Advanced AI Systems

Josh A. Goldstein

and Girish Sastry

March 2025

As new advanced AI systems roll out, there is widespread disagreement about malicious use risks. Are bad actors likely to misuse these tools for harm? This report presents a simple framework to guide the questions researchers ask—and the tools they use—to evaluate the likelihood of malicious use.

Download Full Report

Related Content

Artificial Intelligence incidents have been occurring with the rapid advancement of AI capabilities over the past decade. However, there is not yet a concerted policy effort in the United States to monitor, document, and aggregate… Read More

Analysis

Adding Structure to AI Harm

July 2023

Real-world harms caused by the use of AI technologies are widespread. Tracking and analyzing them improves our understanding of the variety of harms and the circumstances that lead to their occurrence once AI systems are… Read More

Machine learning advances have powered the development of new and more powerful generative language models. These systems are increasingly able to write text at near human levels. In a new report, authors at CSET, OpenAI,… Read More