Adversarial Attack and Defense Strategies for Deep Speaker Recognition Systems

@article{Jati2021AdversarialAA,
  title={Adversarial Attack and Defense Strategies for Deep Speaker Recognition Systems},
  author={Arindam Jati and Chin-Cheng Hsu and Monisankha Pal and Raghuveer Peri and Wael AbdAlmageed and Shrikanth S. Narayanan},
  journal={Comput. Speech Lang.},
  year={2021},
  volume={68},
  pages={101199}
}
Robust speaker recognition, including in the presence of malicious attacks, is becoming increasingly important and essential, especially due to the proliferation of several smart speakers and personal agents that interact with an individual's voice commands to perform diverse, and even sensitive tasks. Adversarial attack is a recently revived domain which is shown to be effective in breaking deep neural network-based classifiers, specifically, by forcing them to change their posterior… Expand
3 Citations

References

SHOWING 1-10 OF 51 REFERENCES
Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems
  • 16
  • PDF
Fooling End-To-End Speaker Verification With Adversarial Examples
  • 79
  • PDF
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
  • 112
  • PDF
Towards Deep Learning Models Resistant to Adversarial Attacks
  • 3,252
  • Highly Influential
  • PDF
Adversarial Attacks on GMM I-Vector Based Speaker Verification Systems
  • 17
  • PDF
Adversarial Regularization for End-to-End Robust Speaker Verification
  • 9
  • PDF
Towards Evaluating the Robustness of Neural Networks
  • 3,306
  • Highly Influential
  • PDF
Metric Learning for Adversarial Robustness
  • 53
  • PDF
Evasion Attacks against Machine Learning at Test Time
  • 1,042
  • PDF
The Limitations of Deep Learning in Adversarial Settings
  • 2,026
  • PDF
...
1
2
3
4
5
...