| 4 | | Adversarial samples are intentionally designed to mislead trained machine learning models into making wrong predictions. This project will leverage adversarial machine learning techniques to attack voice controllable systems. |
| | 4 | This project aims to study the security of voice assistance systems under adversarial machine learning. The audio adversarial samples generated by adversarial learning algorithms can be played via a loudspeaker and recorded with the microphone of voice assistance systems so as to fool the machine learning models in the system. To make the adversarial samples robust under audio propagation, the room impulse response needs to be estimated and used in the adversarial sample generation process. Specifically, the room impulse response and adversarial attack scenarios can be conducted in digital domain or simulated for the over-the-air scenarios using Python or Matlab. |
| | 5 | |
| | 6 | == Tutorials == |
| | 7 | - Generating Adversarial Samples in Keras: https://medium.com/mindboard/generating-adversarial-samples-in-keras-tutorial-f881ac836246 |
| | 8 | - Tensorflow - Adversarial Example using FGSM: https://www.tensorflow.org/tutorials/generative/adversarial_fgsm |
| | 9 | - Generating Adversarial Samples in Keras: https://medium.com/analytics-vidhya/implementing-adversarial-attacks-and-defenses-in-keras-tensorflow-2-0-cab6120c5715 |
