attacks.py 文件源码

def get_gradient_sign_tf(x, predictions):
    """
    TensorFlow implementation of calculting signed gradient with respect to x.
    :param x: the input placeholder
    :param predictions: the model's output tensor
    :return: a tensor for the adversarial example
    """

    # Compute loss
    y = tf.to_float(tf.equal(predictions, tf.reduce_max(predictions, 1, keep_dims=True)))
    y = y / tf.reduce_sum(y, 1, keep_dims=True)
    loss = utils_tf.tf_model_loss(y, predictions, mean=False)

    # Define gradient of loss wrt input
    grad, = tf.gradients(loss, x)

    # Take sign of gradient
    signed_grad = tf.sign(grad)
    signed_grad = tf.stop_gradient(signed_grad)
    return signed_grad