This article considers a problem of security in a computer systems in context of some mechanisms which act in societies and which mechanisms are seen as being useful to assure security in a computer system. A new approach to the security problem is discussed, which refers to identifying computer resource (e.g. agent, program) on the basis of this resource behaviour (actions which this resource undertakes). Mechanisms are presented, which may enable to recognize and dismiss resources undesirable or harmful in the computer system on the basis of behavior observation. Proposed mechanisms were tested in simulations of the computer system under DoS attack. The results of tests are presented and discussed.
展开▼