Hidden Voice Commands
Explore this paper's citation graph
Summary
This paper explores in this paper how voice interfaces can be attacked with hidden voice commands that are unintelligible to human listeners but which are interpreted as commands by devices.
- Type
- article
- Published
- 2016-08-10
- Cited by
- 686
- References
- 50
- OpenAlex
- https://openalex.org/W2486441166
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:6217368
Keywords
Computer science, Voice command device, Oracle, Adversary, Black box
References
- Decaptcha: Breaking 75% of eBay Audio CAPTCHAs
- Cocaine Noodles: Exploiting the Gap between Human and Machine Speech Recognition
- Crying Wolf: An Empirical Study of SSL Warning Effectiveness
- Intriguing properties of neural networks
- Analysis of classifiers’ robustness to adversarial perturbations
- Combining Statistical Parameteric Speech Synthesis and Unit-Selection for Automatic Voice Cloning
- Understanding deep image representations by inverting them
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
- Facilitation in recognizing pairs of words: evidence of a dependence between retrieval operations.
- Your Voice Assistant is Mine: How to Abuse Speakers to Steal Information and Control Your Phone
- Reducing the Cost of Breaking Audio CAPTCHAs by Active and Semi-supervised Learning
- Do security toolbars actually prevent phishing attacks?
- Constructing Secure Audio CAPTCHAs by Exploiting Differences between Humans and Machines
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
- Approaches to adversarial drift
- Cepstral domain segmental feature vector normalization for noise robust speech recognition
- An experimental comparison of naive Bayesian and keyword-based anti-spam filtering with personal e-mail messages
- Adversarial machine learning
- Design of the CMU sphinx-4 decoder
- The security of machine learning
Cited by
- 'Midwives Overboard!' Inside their hearts are breaking, their makeup may be flaking but their smile still stays on.
- Power Allocation for Conventional and Buffer-Aided Link Adaptive Relaying Systems with Energy Harvesting Nodes
- Theory of Metal Surfaces: Work Function
- Theater and the Rites of "Post-Negritude" Remembering
- On the Reliability Function of the Discrete Memoryless Relay Channel
- Adversarial examples in the physical world
- Towards Evaluating the Robustness of Neural Networks
- Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition
- Security of CCTV and Video Surveillance Systems: Threats, Vulnerabilities, Attacks, and Mitigations
- SoK: Security and Privacy in Machine Learning
- Continuous Authentication for Voice Assistants
- Robust image classification: analysis and applications
- Follow But No Track: Privacy Preserved Profile Publishing in Cyber-Physical Social Systems
- Using Program Analysis to Synthesize Sensor Spoofing Attacks
- Deceiving Google’s Cloud Video Intelligence API Built for Summarizing Videos
- Understanding IoT Security Through the Data Crystal Ball: Where We Are Now and Where We Are Going to Be
- PIANO: Proximity-Based User Authentication on Voice-Powered Internet-of-Things Devices
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- Taming Evasions in Machine Learning Based Detection Pipelines
- Google's Cloud Vision API is Not Robust to Noise