[2506.05296] Control Tax: The Price of Keeping AI in Check

Computer Science > Artificial Intelligence arXiv:2506.05296 (cs) [Submitted on 5 Jun 2025 (v1), last revised 2 Mar 2026 (this version, v3)] Title:Control Tax: The Price of Keeping AI in Check Authors:Mikhail Terekhov, Zhen Ning David Liu, Caglar Gulcehre, Samuel Albanie View a PDF of the paper titled Control Tax: The Price of Keeping AI in Check, by Mikhail Terekhov and 3 other authors View PDF HTML (experimental) Abstract:The rapid integration of agentic AI into high-stakes real-world applications requires robust oversight mechanisms. The emerging field of AI Control (AIC) aims to provide such an oversight mechanism, but practical adoption depends heavily on implementation overhead. To study this problem better, we introduce the notion of Control tax -- the operational and financial cost of integrating control measures into AI pipelines. Our work makes three key contributions to the field of AIC: (1) we introduce a theoretical framework that quantifies the Control Tax and maps classifier performance to safety assurances; (2) we conduct comprehensive evaluations of state-of-the-art language models in adversarial settings, where attacker models insert subtle backdoors into code while monitoring models attempt to detect these vulnerabilities; and (3) we provide empirical financial cost estimates for control protocols and develop optimized monitoring strategies that balance safety and cost-effectiveness while accounting for practical constraints like auditing budgets. Our fra...