Strengthening speech content authentication against tampering

Abstract

It is vital to authenticate the content of speech signals to prevent the framing of innocent individuals. Furthermore, lack of speech content authentication may lead to repudiation. The research problem of authenticity vs falsehood is timely considering the recent worldwide interest in fake news and viral manipulated media. Liu & Wang proposed an algorithm to detect tamperings in speech content, based on semi-fragile watermarking. These techniques embed a watermark imperceptibly in the speech signal. Semantic changes to the speech will destroy the watermark, while signal processing operations will not affect the watermark. One main criterion for these speech content authentication schemes is the ability to withstand tampering attacks. We present a cryptanalysis attack framework for watermark based media authentication schemes. To exemplify this, two media authentication schemes and corresponding attacks are modelled within this framework. We discuss the main reasons leading to the attacks and propose a strategy to strengthen the Liu & Wang algorithm against such attacks.