IDENTIFICATION POTENTIAL OF REPRODUCING HANDWRITTEN PASSWORDS
B. N. Epifantsev1, P. S. Lozhnikov2, A. E. Sulavko2, S. S. Zhumazhanova1
1Siberian State Automobile and Highway Academy, pr. Mira 5, Omsk, 644080 Russia
2Omsk State Technical University, pr. Mira 11, Omsk, 644050 Russia
Keywords: информационная безопасность, подсознательные движения, идентификация подписантов, искусственный интеллект, естественный интеллект, сравнение возможностей интеллектов, идентификация состояний субъекта, information security, subconscious movements, signer identification, artificial intelligence, natural intelligence, intelligence comparison, subject state identification
Abstract
This paper presents a comparison of the capabilities of natural and artificial intelligences in problems of identifying operators of information-processing systems and their functional state based on the features of writing handwritten passwords. The cause of the significant spread in the subject identification error probability as determined. It is concluded that at the present level of knowledge, the best result achieved in solving the problem by artificial intelligence systems is close to that potentially possible. It is demonstrated that the use of features of reproducing handwritten passwords is suitable for recognizing the functional state of operators of human-machine systems in professional activities.
|
