2023/11/16 by Kathrin Grosse, Grosse, Kathrin, Lukas Bieringer +6 · 1 voice · 13 citations
Computer Science · #Advanced Malware Detection Techniques #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Information and Cyber Security #Network Security and Intrusion Detection #cs.AI #cs.CR
paper · pdf · doi:10.48550/arxiv.2311.09994
openalex publication_date 2023/11/16 · arxiv published 2023/11/16 · arxiv updated 2024/03/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent works have identified a gap between research and practice in artificial intelligence security: threats studied in academia do not always reflect the practical use and security risks of AI. For example, while models are often studied in isolation, they form part of larger ML pipelines in practice. Recent works also brought forward that adversarial manipulations introduced by academic attacks are impractical. We take a first step towards describing the full extent of this disparity. To this end, we revisit the threat models of the six most studied attacks in AI security research and match them to AI usage in practice via a survey with 271 industrial practitioners. On the one hand, we find that all existing threat models are indeed applicable. On the other hand, there are significant mismatches: research is often too generous with the attacker, assuming access to information not frequently available in real-world settings. Our paper is thus a call for action to study more practical threat models in artificial intelligence security.