SoK: On the Offensive Potential of AI
Saskia Laura Schr\"oer, Giovanni Apruzzese, Soheil Human, Pavel, Laskov, Hyrum S. Anderson, Edward W. N. Bernroider, Aurore Fass, Ben Nassi,, Vera Rimmer, Fabio Roli, Samer Salam, Ashley Shen, Ali Sunyaev, Tim, Wadhwa-Brown, Isabel Wagner, Gang Wang

TL;DR
This paper systematically analyzes the offensive potential of AI by consolidating diverse sources of knowledge, revealing concerning offensive capabilities and providing a foundation for future threat mitigation.
Contribution
It introduces a comprehensive framework for assessing offensive AI capabilities by integrating academic, industrial, expert, and lay perspectives.
Findings
Identifies new offensive AI use cases overlooked by prior work
Provides a systematic analysis of 95 research papers and 38 briefings
Highlights diverse offensive AI threats across different domains
Abstract
Our society increasingly benefits from Artificial Intelligence (AI). Unfortunately, more and more evidence shows that AI is also used for offensive purposes. Prior works have revealed various examples of use cases in which the deployment of AI can lead to violation of security and privacy objectives. No extant work, however, has been able to draw a holistic picture of the offensive potential of AI. In this SoK paper we seek to lay the ground for a systematic analysis of the heterogeneous capabilities of offensive AI. In particular we (i) account for AI risks to both humans and systems while (ii) consolidating and distilling knowledge from academic literature, expert opinions, industrial venues, as well as laypeople -- all of which being valuable sources of information on offensive AI. To enable alignment of such diverse sources of knowledge, we devise a common set of criteria…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBig Data and Digital Economy · Computability, Logic, AI Algorithms
MethodsSparse Evolutionary Training
