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

Thunderclap: Exploring Vulnerabilities in Operating System IOMMU Protection via...

A. Theodore Markettos (University of Cambridge), Colin Rothwell (University of Cambridge), Brett F. Gutstein (Rice University), Allison Pearce (University of Cambridge), Peter G. Neumann (SRI International), Simon W. Moore (University of Cambridge), Robert N. M. Watson (University of Cambridge)

Read More

maTLS: How to Make TLS middlebox-aware?

Hyunwoo Lee (Seoul National University), Zach Smith (University of Luxembourg), Junghwan Lim (Seoul National University), Gyeongjae Choi (Seoul National University), Selin Chun (Seoul National University), Taejoong Chung (Rochester Institute of Technology), Ted "Taekyoung" Kwon (Seoul National University)

Read More

Neural Machine Translation Inspired Binary Code Similarity Comparison beyond...

Fei Zuo (University of South Carolina), Xiaopeng Li (University of South Carolina), Patrick Young (Temple University), Lannan Luo (University of South Carolina), Qiang Zeng (University of South Carolina), Zhexin Zhang (University of South Carolina)

Read More

NIC: Detecting Adversarial Samples with Neural Network Invariant Checking

Shiqing Ma (Purdue University), Yingqi Liu (Purdue University), Guanhong Tao (Purdue University), Wen-Chuan Lee (Purdue University), Xiangyu Zhang (Purdue University)

Read More