all InfoSec news
VenoMave: Targeted Poisoning Against Speech Recognition. (arXiv:2010.10682v3 [cs.SD] UPDATED)
cs.CR updates on arXiv.org arxiv.org
Despite remarkable improvements, automatic speech recognition is susceptible
to adversarial perturbations. Compared to standard machine learning
architectures, these attacks are significantly more challenging, especially
since the inputs to a speech recognition system are time series that contain
both acoustic and linguistic properties of speech. Extracting all
recognition-relevant information requires more complex pipelines and an
ensemble of specialized components. Consequently, an attacker needs to consider
the entire pipeline. In this paper, we present VENOMAVE, the first
training-time poisoning attack against speech …
acoustic adversarial attack attacks automatic evasion information inputs linguistic machine machine learning pipeline pipelines poisoning recognition series speech standard system training