Doklady Mathematics. Vol. 106, No. 1, Pages S9-S13, 2022

D. Yu. Turdakov^a^,^d^,^f^,*, Academician of the RAS A. I. Avetisyan^a^,^d^,^e^,^f, K. V. Arkhipenko^a, A. V. Antsiferova^a, D. S. Vatolin^d, S. S. Volkov^a, A. V. Gasnikov^a^,^e, D. A. Devyatkin^d^,^g, M. D. Drobyshevsky^a^,^e, A. P. Kovalenko^a, M. I. Krivonosov^a, N. V. Lukashevich^d, V. A. Malykh^e, S. I. Nikolenko^f, I. V. Oseledets^b^,^c, A. I. Perminov^a^,^d, I. V. Sochenkov^b^,^g, M. M. Tikhomirov^d, A. N. Fedotov^d, and M. Yu. Khachay^h

^aIvannikov Institute for System Programming, Russian Academy of Sciences, Moscow, Russia

^eMoscow Institute of Physics and Technology (National Research University), Dolgoprudnyi, Moscow oblast, Russia

^gInstitute for Systems Analysis, Federal Research Center “Computer Science and Control,” Russian Academy of Sciences, Moscow, Russia

^hKrasovskii Institute of Mathematics and Mechanics, Ural Branch, Russian Academy of Sciences, Yekaterinburg, Russia

Abstract—Wide applications of artificial intelligence technologies have led to new threats that cannot be effectively addressed using current tools for secure software development. To meet the challenge, the Research Center for Trusted Artificial Intelligence based on the Institute for Systems Analysis of the Russian Academy of Sciences was founded within the federal project “Artificial Intelligence” in 2021. Its objectives are the creation of scientific and technological basis for building trust in AI technologies. This paper discusses the risks and threats of applying artificial intelligence technologies, and describes the research directions and intermediate results produced at the Research Center for Trusted Artificial Intelligence.

Keywords: trusted artificial intelligence, attacks on machine learning, explainable artificial intelligence, trusted intelligent systems

Trusted Artificial Intelligence: Challenges and Promising Solutions