V. Bernard, P-Y. Cousin, A. Lefaillet, M. Mugaruka and C. Raibaud, Paris School of Engineering, France

With the generalization of mobile communication systems, solicitations of all kinds in the form of messages and emails are received by users with increasing proportion of malicious ones. They are customized to pass anti-spam filters and ask the person to click or to open the joined dangerous attachment. Current filters are very inefficient against spear phishing emails. It is proposed to improve the existing filters by taking advantage of user own analysis and feedback to detect all kinds of phishing emails. The method rests upon an interface displaying different warnings to receivers. Analysis shows that users trust their first impression and are often lead to ignore warnings flagged by proposed new interactive system.

Phishing, Spam, Human Sensors, User-based Paper