[general_dat] Seminario AISAR – Control Tax: The Price of Keeping AI in Check

[Agustín Martinez Suñé]

Desde el Programa de Becas AISAR en AI Safety tenemos el placer de
invitarlos a la próxima charla de nuestro seminario online, con la
participación de investigadores del área.

📌 Fecha y hora: Miércoles 8 de octubre, 10:00 hs (ARG).
🎤 Orador: Mikhail Terekhov – Doctoral Student @ EPFL | Scholar @ MATS
📖 Título: Control Tax: The Price of Keeping AI in Check

[image: 🌐] [image: 👉] Charla online, Inscripción: Para asistir a la
charla, por favor indicá tu nombre en el siguiente formulario (No es
necesario que completes este formulario si ya indicaste "Quiero que me
avisen por correo electrónico cuando haya nuevas charlas de AISAR" en un
formulario previo): https://forms.gle/4b3t74DkzYiWkcJZ6

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 framework enables practitioners to
make informed decisions by systematically connecting safety guarantees with
their costs, advancing AIC through principled economic feasibility
assessment across different deployment contexts.

Encontrá el paper acá: https://arxiv.org/abs/2506.05296
Equipo AISAR
http://scholarship.aisafety.ar/
<http://scholarship.aisafety.ar/?utm_source=chatgpt.com>