Are facial attributes adversarially robust?

@article{Rozsa2016AreFA,
  title={Are facial attributes adversarially robust?},
  author={Andras Rozsa and M. G{\"u}nther and Ethan M. Rudd and T. Boult},
  journal={2016 23rd International Conference on Pattern Recognition (ICPR)},
  year={2016},
  pages={3121-3127}
}
  • Andras Rozsa, M. Günther, +1 author T. Boult
  • Published 2016
  • Computer Science
  • 2016 23rd International Conference on Pattern Recognition (ICPR)
  • Facial attributes are emerging soft biometrics that have the potential to reject non-matches, for example, based on mismatching gender. To be usable in stand-alone systems, facial attributes must be extracted from images automatically and reliably. In this paper, we propose a simple yet effective solution for automatic facial attribute extraction by training a deep convolutional neural network (DCNN) for each facial attribute separately, without using any pre-training or dataset augmentation… CONTINUE READING
    Facial Attributes: Accuracy and Adversarial Robustness
    • 26
    • PDF
    AFFACT: Alignment-free facial attribute classification technique
    • 39
    • PDF
    PrivacyNet: Semi-Adversarial Networks for Multi-Attribute Face Privacy
    • 6
    • PDF
    Soft biometric privacy: Retaining biometric utility of face images while perturbing gender
    • 34
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 25 REFERENCES
    Deep Learning Face Attributes in the Wild
    • 2,686
    • Highly Influential
    • PDF
    Attribute and simile classifiers for face verification
    • 1,353
    • PDF
    Adversarial Diversity and Hard Positive Generation
    • 130
    • PDF
    Describable Visual Attributes for Face Verification and Image Search
    • 436
    • PDF
    Adversarial Manipulation of Deep Representations
    • 159
    • PDF
    FaceTracer: A Search Engine for Large Collections of Images with Faces
    • 367
    • PDF
    Intriguing properties of neural networks
    • 5,202
    • PDF
    Deep Face Recognition
    • 2,976
    • PDF
    Explaining and Harnessing Adversarial Examples
    • 5,490
    • Highly Influential
    • PDF