M.Com. (Computer Auditing) / Knowledge-based systems (KBS's) is one of the new and emerging technologies, and it is expected to impact dramatically on the information systems of the 1990's. As many of these systems impact business operations and have significant financial influence, auditors should be involved in the implementation of this emerging technology and should review it for the presence and continued operation of effective controls. Because this technology up to now has been tried only in limited environments, the relevant risk, control and audit issues are not always clearly defined. The objective of this essay will be to identify the risks, controls and audit considerations in a knowledge-based system environment, with special reference to neural networks. As neural networks have got the ability to modify themselves without any human intervention, this can have major audit implications - a topic which has not been dealt with before by the audit community.