Giters

Trusted-AI / adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Home Page:https://adversarial-robustness-toolbox.readthedocs.io/en/latest/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

adversarial audio example notebook not giving the same results

3DVERSEjn opened this issue · comments

commented
Screenshot 2024-04-11 at 12 34 49 PM This is what I am getting from the tutorial notebook. It does not match to the original outputs from the repo.
commented

Hi @3DVERSEjn ,Thank you very much for reporting your observations. Could you please provide more details about your experiments?

commented

Yes I am simply running the provided notebooks for speech models. In particular this notebook result above comes from the adversarial audio example. When running the attack we get an audio file that contains only white noise, the original audio can no longer be heard.