Responsible Development of Offensive AI
It addresses the need for consensus in AI research priorities to mitigate risks from offensive technologies, but is incremental as it builds on existing frameworks.
The paper tackles the problem of prioritizing research in offensive AI by evaluating vulnerability detection agents and AI-powered malware, using Sustainable Development Goals and interpretability techniques to balance societal benefits and risks.
As AI advances, broader consensus is needed to determine research priorities. This endeavor discusses offensive AI and provides guidance by leveraging Sustainable Development Goals (SDGs) and interpretability techniques. The objective is to more effectively establish priorities that balance societal benefits against risks. The two forms of offensive AI evaluated in this study are vulnerability detection agents, which solve Capture- The-Flag challenges, and AI-powered malware.