The Crux of Voice (In)Security: A Brain Study of Speaker Legitimacy Detection

Abstract

A new generation of scams has emerged that uses voice impersonation to obtain sensitive information, eavesdrop over voice calls and extort money from unsuspecting human users. Research demonstrates that users are fallible to voice impersonation attacks that exploit the current advancement in speech synthesis. In this paper, we set out to elicit a deeper understanding of such human-centered “voice hacking” based on a neuro-scientific methodology (thereby corroborating and expanding the traditional behavioral-only approach in significant ways). Specifically, we investigate the neural underpinnings of voice security through functional near-infrared spectroscopy (fNIRS), a cutting-edge neuroimaging technique, that captures neural signals in both temporal and spatial domains. We design and conduct an fNIRS study to pursue a thorough investigation of users’ mental processing related to speaker legitimacy detection –whether a voice sample is rendered by a target speaker, a different other human speaker or a synthesizer mimicking the speaker. We analyze the neural activity associated within this task as well as the brain areas that may control such activity. Our key insight is that there may be no statistically significant differences in the way the human brain processes the legitimate speakers vs. synthesized speakers, whereas clear differences are visible when encountering legitimate vs. different other human speakers. This finding may help to explain users’ susceptibility to synthesized attacks, as seen from the behavioral self-reported analysis. That is, the impersonated synthesized voices may seem indistinguishable from the real voices in terms of both behavioral and neural perspectives. In sharp contrast, prior studies showed subconscious neural differences in other real vs. fake artifacts (e.g., paintings and websites), despite users failing to note these differences behaviorally. Overall, our work dissects the fundamental neural patterns underlying voice-based insecurity and reveals users’ susceptibility to voice synthesis attacks at a biological level. We believe that this could be a significant insight for the security community suggesting that the human detection of voice synthesis attacks may not improve over time, especially given that voice synthesis techniques will likely continue to improve, calling for the design of careful machine-assisted techniques to help humans counter these attacks.