convex_adversarial software on GitHub

Software OPEN SOURCE
  • Subject:
    arxiv: Computer Science::Cryptography and Security | Quantitative Biology::Neurons and Cognition | Computer Science::Neural and Evolutionary Computation | Computer Science::Multimedia
    acm: TheoryofComputation_MISCELLANEOUS | ComputingMethodologies_GENERAL

A method for training neural networks that are provably robust to adversarial attacks.
Share - Bookmark