The Malicious Use of Artificial Intelligence
Recorded: Sept. 14, 2026, 3 a.m.
| Original | Summarized |
[1802.07228] The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
Skip to main content Search Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:1802.07228 (cs) [Submitted on 20 Feb 2018 (v1), last revised 1 Dec 2024 (this version, v2)] Abstract:This report surveys the landscape of potential security threats from malicious uses of AI, and proposes ways to better forecast, prevent, and mitigate these threats. After analyzing the ways in which AI may influence the threat landscape in the digital, physical, and political domains, we make four high-level recommendations for AI researchers and other stakeholders. We also suggest several promising areas for further research that could expand the portfolio of defenses, or make attacks less effective or harder to execute. Finally, we discuss, but do not conclusively resolve, the long-term equilibrium of attackers and defenders. Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Computers and Society (cs.CY) Cite as: Focus to learn more arXiv-issued DOI via DataCite Submission history From: Miles Brundage [view email] [v1]
Full-text links: View a PDF of the paper titled The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation, by Miles Brundage and 25 other authorsView PDF < prev | new Change to browse by: References & Citations NASA ADSGoogle Scholar 2 blog links (what is this?) DBLP - CS Bibliography listing | bibtex Miles BrundageShahar AvinJack ClarkHelen TonerPeter Eckersley … export BibTeX citation BibTeX formatted citation loading... Data provided by: Bookmark
Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author About arXivLabs arXivLabs: experimental projects with community collaborators Which authors of this paper are endorsers? | We gratefully acknowledge support from About Major funding support from |
This report examines the landscape of security threats stemming from the malicious application of artificial intelligence and proposes frameworks for forecasting, preventing, and mitigating these risks. The analysis delves into how artificial intelligence can influence threat landscapes across the digital, physical, and political domains. Based on this exploration, the authors put forward four high-level recommendations aimed at AI researchers and other stakeholders. Furthermore, the report suggests several promising avenues for future research intended to expand the portfolio of defenses or render attacks less effective and more difficult to execute. The discussion also addresses the long-term equilibrium between attackers and defenders in the context of malicious artificial intelligence. |