Audio Adversarial Examples: Targeted Attacks on Speech-to-Text

Keywords

Adversarial system, Computer science, Phrase, Speech recognition, Construct (python library)

References

• Intriguing properties of neural networksChristian Szegedy, Wojciech Zaremba, Ilya Sutskever — 2013
• Deep Speech: Scaling up end-to-end speech recognitionAwni Hannun, Carl Case, Jared Casper — 2014
• Deep neural networks are easily fooled: High confidence predictions for unrecognizable imagesAnh‐Tu Nguyen, Jason Yosinski, Jeff Clune — 2014
• Deep Learning and Music AdversariesCorey Kereliuk, Bob L. Sturm, Jan Larsen — 2015
• Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber — 1997
• The security of machine learningMarco Barreno, Blaine Nelson, Anthony D. Joseph — 2010
• Connectionist temporal classificationAlex Graves, Santiago Fernández, Faustino Gomez — 2006
• Can machine learning be secure?Marco Barreno, Blaine Nelson, Russell Sears — 2006
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional ComputationYoshua Bengio, Nicholas Léonard, Aaron Courville — 2013
• Practical Black-Box Attacks against Deep Learning Systems using Adversarial ExamplesNicolas Papernot, Patrick McDaniel, Ian Goodfellow — 2016
• Adversarial learningDaniel Lowd, Christopher Meek — 2005
• Adversarial Diversity and Hard Positive GenerationAndras Rozsa, Ethan M. Rudd, Terrance E. Boult — 2016
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial SamplesNicolas Papernot, Patrick McDaniel, Ian Goodfellow — 2016
• Adversarial Perturbations Against Deep Neural Networks for Malware ClassificationKathrin Grosse, Nicolas Papernot, Praveen Manoharan — 2016
• Adversarial examples in the physical worldAlexey Kurakin, Ian Goodfellow, Samy Bengio — 2016
• Hidden Voice CommandsNicholas Carlini, Pratyush Mishra, Tavish Vaidya — 2016
• A study of the effect of JPG compression on adversarial imagesGintare Karolina Dziugaite, Zoubin Ghahramani, Daniel M. Roy — 2016
• Towards Evaluating the Robustness of Neural NetworksNicholas Carlini, David Wagner — 2016
• Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face RecognitionMahmood Sharif, Sruti Bhagavatula, Lujo Bauer — 2016
• Universal Adversarial PerturbationsSeyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi — 2016

Cited by

• Deep packet: a novel approach for encrypted traffic classification using deep learningMohammad Lotfollahi, Mahdi Jafari Siavoshani, Ramin Shirali Hossein Zade — 2017
• Crafting Adversarial Examples For Speech Paralinguistics ApplicationsYuan Gong, Christian Poellabauer — 2017
• Adversarial frontier stitching for remote neural network watermarkingErwan Le Merrer, Patrick Pérez, Gilles Trédan — 2017
• Fooling OCR Systems with Adversarial Text ImagesCongzheng Song, Vitaly Shmatikov — 2018
• Detecting Adversarial Examples via Neural FingerprintingSumanth Dathathri, Stephan Zheng, Yin, Tianwei — 2018
• Explanation Methods in Deep Learning: Users, Values, Concerns and ChallengesGabriëlle Ras, Marcel van Gerven, Pim Haselager — 2018
• An Overview of Vulnerabilities of Voice Controlled SystemsYuan Gong, Christian Poellabauer — 2018
• Attacking convolutional neural network using differential evolutionJiawei Su, Danilo Vargas, Kouichi Sakurai — 2018
• Is automatic speech-to-text transcription ready for use in psychological experiments?Kirsten Ziman, Andrew C. Heusser, Paxton C. Fitzpatrick — 2018
• Improving Network Intrusion Detection Classifiers by Non-payload-Based Exploit-Independent Obfuscations: An Adversarial ApproachIvan Homoliak, Martin Teknös, Martín Ochoa — 2018
• PRADA: Protecting Against DNN Model Stealing AttacksMika Juuti, Sebastian Szyller, Samuel Marchal — 2018
• DIoT: A Self-learning System for Detecting Compromised IoT DevicesThien Duc Nguyen, Samuel Marchal, Markus Miettinen — 2018
• Targeted Adversarial Examples for Black Box Audio SystemsRohan Taori, Amog Kamsetty, Brenton Chu — 2018
• Deep Generative Models for Semi-Supervised Machine LearningLars Maaløe — 2018
• POSTER: I Can't Hear This Because I Am Human: A Novel Design of Audio CAPTCHA SystemJusop Choi, Taekkyung Oh, William Aiken — 2018
• Training Augmentation with Adversarial Examples for Robust Speech RecognitionSining Sun, Ching-Feng Yeh, Mari Ostendorf — 2018
• Interpreting Deep Learning: The Machine Learning Rorschach Test?Adam S. Charles — 2018
• POSTER: DeepCRACk: Using Deep Learning to Automatically CRack Audio CAPTCHAsWilliam Aiken, Hyoungshick Kim — 2018
• ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for AudioNilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen — 2018
• Built-in Vulnerabilities to Imperceptible Adversarial PerturbationsThomas Tanay, Jerone T. A. Andrews, Lewis D. Griffin — 2018

Related papers

• DeepFool: A Simple and Accurate Method to Fool Deep Neural NetworksSeyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Pascal Frossard — 2015
• Adversarial examples in the physical worldAlexey Kurakin, Ian Goodfellow, Samy Bengio — 2016
• Practical Black-Box Attacks against Machine LearningNicolas Papernot, Patrick McDaniel, Ian Goodfellow — 2016
• The Limitations of Deep Learning in Adversarial SettingsNicolas Papernot, Patrick McDaniel, Somesh Jha — 2015
• Deep Residual Learning for Image RecognitionKaiming He, Xiangyu Zhang, Shaoqing Ren — 2015
• Universal Adversarial PerturbationsSeyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi — 2016