search

gongzhitaao / tensorflow-adversarial

Crafting adversarial images
MIT License
223 stars 70 forks source link

what is adversarial data? #4

Closed Mistty closed 6 years ago

Mistty commented 6 years ago

recently I am working on model compression and if it influenced model robustness while facing adversarial samples, I tried ex06.py on cifar10, and after generating adversarial data, it would test against adversarial test data: print('Testing against adversarial test data') score = model.evaluate(X_adv, y_test) print('\nloss: {0:.4f} acc: {1:.4f}'.format(score[0], score[1])) I am a little confused, higher accuracy means better or worse robustness? or it's not related? so could you please explain a little about adversarial data, thx!

gongzhitaao commented 6 years ago

Higher accuracy means the model is more robust or the adversarial samples are not very effective.

Mistty commented 6 years ago

Thank you very much! Really helps!