Login / Signup

Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning.

Eldor AbdukhamidovMohammed AbuhamadSimon S. WooEric Chan-TinTamer Abuhmed
Published in: CoRR (2022)
Keyphrases
  • deep learning
  • unsupervised learning
  • data sets
  • machine learning
  • pattern recognition
  • decision making
  • decision trees
  • face recognition
  • deep architectures
  • unsupervised feature learning