<ul><li>The offensive potential of AI is a growing concern in society, with evidence showing its use in violating security and privacy objectives.</li><li>This paper aims to provide a systematic analysis of the heterogeneous capabilities of offensive AI, considering risks to humans and systems.</li><li>The authors analyze 95 research papers, 38 InfoSec briefings, a user study with 549 individuals, and the opinions of 12 experts to reveal overlooked ways in which AI can be used offensively.</li><li>The findings not only highlight current threats but also lay the groundwork for addressing this issue in the future.</li></ul>

SoK: On the Offensive Potential of AI

Discover more