Lea Schönherr (Ruhr University Bochum), Katharina Kohls (Ruhr University Bochum), Steffen Zeiler (Ruhr University Bochum), Thorsten Holz (Ruhr University Bochum), Dorothea Kolossa (Ruhr University Bochum)

Voice interfaces are becoming accepted widely as input methods for a diverse set of devices. This development is driven by rapid improvements in automatic speech recognition (ASR), which now performs on par with human listening in many tasks. These improvements base on an ongoing evolution of deep neural networks (DNNs) as the computational core of ASR. However, recent research results show that DNNs are vulnerable to adversarial perturbations, which allow attackers to force the transcription into a malicious output.

In this paper, we introduce a new type of adversarial examples based on *psychoacoustic hiding*. Our attack exploits the characteristics of DNN-based ASR systems, where we extend the original analysis procedure by an additional backpropagation step. We use this backpropagation to learn the degrees of freedom for the adversarial perturbation of the input signal, i.e., we apply a psychoacoustic model and manipulate the acoustic signal below the thresholds of human perception. To further minimize perceptibility of the perturbations, we use forced alignment to find the best fitting temporal alignment between the original audio sample and the malicious target transcription. These extensions allow us to embed an arbitrary audio input with a malicious voice command that is then transcribed by the ASR system, with the audio signal remaining barely distinguishable from the original signal. In an experimental evaluation, we attack the state-of-the-art speech recognition system *Kaldi* and determine the best performing parameter and analysis setup for different types of input. Our results show that we are successful in up to 98% of cases with a computational effort of fewer than two minutes for a ten-second audio file. Based on user studies, we found that none of our target transcriptions were audible to human listeners, who still understand the original speech content with unchanged accuracy.

View More Papers

Privacy Attacks to the 4G and 5G Cellular Paging...

Syed Rafiul Hussain (Purdue University), Mitziu Echeverria (University of Iowa), Omar Chowdhury (University of Iowa), Ninghui Li (Purdue University), Elisa Bertino (Purdue University)

Read More

TIMBER-V: Tag-Isolated Memory Bringing Fine-grained Enclaves to RISC-V

Samuel Weiser (Graz University of Technology), Mario Werner (Graz University of Technology), Ferdinand Brasser (Technische Universität Darmstadt), Maja Malenko (Graz University of Technology), Stefan Mangard (Graz University of Technology), Ahmad-Reza Sadeghi (Technische Universität Darmstadt)

Read More

BadBluetooth: Breaking Android Security Mechanisms via Malicious Bluetooth Peripherals

Fenghao Xu (The Chinese University of Hong Kong), Wenrui Diao (Jinan University), Zhou Li (University of California, Irvine), Jiongyi Chen (The Chinese University of Hong Kong), Kehuan Zhang (The Chinese University of Hong Kong)

Read More

SABRE: Protecting Bitcoin against Routing Attacks

Maria Apostolaki (ETH Zurich), Gian Marti (ETH Zurich), Jan Müller (ETH Zurich), Laurent Vanbever (ETH Zurich)

Read More