RYC-98 / SFVA

Official codes for SFVA (Accepted by Information Sciences)

Crafting transferable adversarial examples via contaminating the salient feature variance

Requirements

• Python 3.6.8
• Keras 2.2.4
• Tensorflow 1.14.0
• Numpy 1.16.2
• Pillow 6.0.0
• Scipy 1.2.1

Experiments

You should download the pretrained models from ( https://github.com/tensorflow/models/tree/master/research/slim, and https://github.com/tensorflow/models/tree/archive/research/adv_imagenet_models) before running the code. Then place these model checkpoint files in ./models_tf.

Main Results

Number of copies $N$ is set to 25.