Stop Bugging Me! Evading Modern-Day Wiretapping Using Adversarial Perturbations
This addresses privacy risks for individuals using VoIP services by evading mass surveillance systems, representing a novel application of adversarial learning in audio security.
The authors tackled the problem of automated surveillance in VoIP conversations by developing a universal adversarial perturbation (UAP) that, when added to audio, prevents topic detection, achieving real-world feasibility across various speakers and applications.
Mass surveillance systems for voice over IP (VoIP) conversations pose a great risk to privacy. These automated systems use learning models to analyze conversations, and calls that involve specific topics are routed to a human agent for further examination. In this study, we present an adversarial-learning-based framework for privacy protection for VoIP conversations. We present a novel method that finds a universal adversarial perturbation (UAP), which, when added to the audio stream, prevents an eavesdropper from automatically detecting the conversation's topic. As shown in our experiments, the UAP is agnostic to the speaker or audio length, and its volume can be changed in real time, as needed. Our real-world solution uses a Teensy microcontroller that acts as an external microphone and adds the UAP to the audio in real time. We examine different speakers, VoIP applications (Skype, Zoom, Slack, and Google Meet), and audio lengths. Our results in the real world suggest that our approach is a feasible solution for privacy protection.