The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding
Open accessAbstract
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 the 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 stateof-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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
The Limitations of Deep Learning in Adversarial Settings
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z. B., & Swami, A. (2016) · 2016 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2016.36 · Cited by 3,993
Practical Black-Box Attacks against Machine Learning
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2017) · Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security · doi:10.1145/3052973.3053009 · Cited by 3,495
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks
Papernot, N., McDaniel, P., Wu, X., Jha, S., & Swami, A. (2016) · 2016 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2016.41 · Cited by 2,982
Universal Adversarial Perturbations
Moosavi-Dezfooli, S.-M., Fawzi, A., Fawzi, O., & Frossard, P. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.17 · Cited by 2,680
Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
Papernot, N., McDaniel, P., & Goodfellow, I. (2016) · arXiv · doi:10.48550/arxiv.1605.07277 · Cited by 1,326
Delving into Transferable Adversarial Examples and Black-box Attacks
Liu, Y., Chen, X., Liu, C., & Song, D. (2016) · arXiv · doi:10.48550/arxiv.1611.02770 · Cited by 1,310
Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi
McAuliffe, M., Socolof, M., Mihuc, S., Wagner, M., & Sonderegger, M. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-1386 · Cited by 1,146
Improved wavelet-based watermarking through pixel-wise masking
Barni, M., Bartolini, F., & Piva, A. (2001) · IEEE Transactions on Image Processing · doi:10.1109/83.918570 · Cited by 961
Black-box Adversarial Attacks with Limited Queries and Information
Ilyas, A., Engstrom, L., Athalye, A., & Lin, J. (2018) · arXiv · doi:10.48550/arxiv.1804.08598 · Cited by 806
Stealing Machine Learning Models via Prediction APIs
Tramèr, F., Zhang, F., Juels, A., Reiter, M. K., & Ristenpart, T. (2016) · arXiv · doi:10.48550/arxiv.1609.02943 · Cited by 796
Perceptual watermarks for digital images and video
Wolfgang, R. B., Podilchuk, C. I., & Delp, E. J. (1999) · Proceedings of the IEEE · doi:10.1109/5.771067 · Cited by 636
Brown, T. B., Mané, D., Roy, A., Abadi, M., & Gilmer, J. (2017) · arXiv · doi:10.48550/arxiv.1712.09665 · Cited by 509
Stealing Hyperparameters in Machine Learning
Wang, B., & Gong, N. Z. (2018) · 2018 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2018.00038 · Cited by 470
PRADA: Protecting Against DNN Model Stealing Attacks
Juuti, M., Szyller, S., Marchal, S., & Asokan, N. (2019) · 2019 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2019.00044 · Cited by 440 · cited 1×
“It may be possible to retrieve the model parameters with different model stealing approaches [51], [36], [56], [39], [24].”
BackgroundShaham, U., Yamada, Y., & Negahban, S. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.04.027 · Cited by 355
English Conversational Telephone Speech Recognition by Humans and Machines
Saon, G., Kurata, G., Sercu, T., Audhkhasi, K., Thomas, S., Dimitriadis, D., Cui, X., Ramabhadran, B., Picheny, M., Lim, L.-L., et al. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-405 · Cited by 349
The microsoft 2016 conversational speech recognition system
Xiong, W., Droppo, J., Huang, X., Seide, F., Seltzer, M., Stolcke, A., Yu, D., & Zweig, G. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7953159 · Cited by 326
Efficient Defenses Against Adversarial Attacks
Zantedeschi, V., Nicolae, M.-I., & Rawat, A. (2017) · Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security · doi:10.1145/3128572.3140449 · Cited by 312
CommanderSong: A Systematic Approach for Practical Adversarial Voice RecognitionPreprint
Yuan, X., Chen, Y., Zhao, Y., Long, Y., Liu, X., Chen, K., Zhang, S., Huang, H., Wang, X., & Gunter, C. A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.08535 · Cited by 269
Houdini: Fooling Deep Structured Prediction ModelsPreprint
Cissé, M., Adi, Y., Neverova, N., & Keshet, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.05373 · Cited by 257
Toward Human Parity in Conversational Speech Recognition
Xiong, W., Droppo, J., Huang, X., Seide, F., Seltzer, M. L., Stolcke, A., Yu, D., & Zweig, G. (2017) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2017.2756440 · Cited by 245
webMUSHRA — A Comprehensive Framework for Web-based Listening Tests
Schoeffler, M., Bartoschek, S., Stöter, F.-R., Roess, M., Westphal, S., Edler, B., & Herre, J. (2018) · Journal of Open Research Software · doi:10.5334/jors.187 · Cited by 236
Robust Physical-World Attacks on Machine Learning Models.Preprint
Evtimov, I., Eykholt, K., Fernandes, E., Kohno, T., Li, B., Prakash, A., Rahmati, A., & Song, D. X. (2017) · arXiv (Cornell University) · Cited by 195
Parseval Networks: Improving Robustness to Adversarial Examples
Cissé, M., Bojanowski, P., Grave, É., Dauphin, Y., & Usunier, N. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.08847 · Cited by 158
Cocaine noodles: exploiting the gap between human and machine speech recognition
Vaidya, T., Zhang, Y., Sherr, M., & Shields, C. (2015) · Cited by 154
Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition
Audhkhasi, K., Kingsbury, B. E. D., Ramabhadran, B., Saon, G., & Picheny, M. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461935 · Cited by 103
Manohar, V., Povey, D., & Khudanpur, S. P. (2017) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2017.8268956 · Cited by 45
A network of deep neural networks for Distant Speech Recognition
Ravanelli, M., Brakel, P., Omologo, M., & Bengio, Y. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953084 · Cited by 39
The Kaldi OpenKWS System: Improving Low Resource Keyword Search
Trmal, J., Wiesner, M., Peddinti, V., Zhang, X., Ghahremani, P., Wang, Y., Manohar, V., Xu, H., Povey, D., & Khudanpur, S. P. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-601 · Cited by 38
Your Voice Assistant is Mine: How to Abuse Speakers to Steal Information and Control Your PhonePreprint
Diao, W., Liu, X., Zhou, Z. G., & Zhang, K. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1407.4923 · Cited by 25
Secure Hybrid Spread Spectrum System for Steganography in Auditive Media
Nutzinger, M., Fabián, C., & Marschalek, M. (2010) · International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP) · doi:10.1109/iihmsp.2010.27 · Cited by 22
Ranjan, S., & Hansen, J. H. L. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-1182 · Cited by 11
Factored Deep Convolutional Neural Networks for Noise Robust Speech Recognition
Fujimoto, M. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-225 · Cited by 10
Cited by
Subpopulation Data Poisoning Attacks
Jagielski, M., Severi, G., Pousette Harger, N., & Oprea, A. (2021) · Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3460120.3485368 · Cited by 86
Joshi, S., Villalba, J., Zelasko, P., Moro-Velazquez, L., & Dehak, N. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3116438 · Cited by 53
FENCE: Feasible Evasion Attacks on Neural Networks in Constrained Environments
Chernikova, A., & Oprea, A. (2022) · ACM Transactions on Privacy and Security · doi:10.1145/3544746 · Cited by 52
Metadata
- Authors
- Schonherr, L., Kohls, K., Zeiler, S., Holz, T., & Kolossa, D.
- Venue
- Proceedings 2019 Network and Distributed System Security Symposium
- Publisher
- Internet Society
- Published
- 2019
- OpenAlex
- W2885407017
- Cited by
- 270
- References
- 37
- FWCI
- 16.53
- Type
- conference paper
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.