GenAttack: practical black-box attacks with gradient-free optimization

    GECCO, pp. 1111-1119, 2019.

    Cited by: 49|Bibtex|Views77|
    EI

    Abstract:

    Deep neural networks are vulnerable to adversarial examples, even in the black-box setting, where the attacker is restricted solely to query access. Existing black-box approaches to generating adversarial examples typically require a significant number of queries, either for training a substitute network or performing gradient estimatio...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments