On Privacy Leakage through Silence Suppression

Abstract

Silence suppression, an essential feature of speech communications over the Internet, saves bandwidth by disabling voice packet transmission when silence is detected. On the other hand, silence suppression enables an adversary to recover talk patterns from packet timing. In this paper, we investigate privacy leakage through the silence suppression feature. More specifically, we propose a new class of traffic analysis attacks to encrypted speech communication with the goal of detecting speakers of encrypted speech communications. We evaluate the proposed attacks by extensive experiments over different type of networks including commercialized anonymity networks and campus networks. The experiments show that the proposed traffic analysis attacks can detect speakers of encrypted speech communications with high detection rates.