Detecting Social Engineering

This paper focuses on detecting social engineering attacks perpetrated over phone lines. Current methods for dealing with social engineering attacks rely on security policies and employee training, which fail because the root of the problem, people, are still involved. Our solution relies on computer systems to analyze phone conversations in real time and determine if the caller is deceiving the receiver. The technologies employed in the proposed Social Engineering Defense Architecture (SEDA) are in the proof-of-concept phase but are, nevertheless, tractable. An important byproduct of this work is the generation of real-time signatures, which can be used in forensic investigations.