GitHub topics: bayesian-per
sisinflab/MSAP
In this work, we extend the FGSM method proposing multistep adversarial perturbation (MSAP) procedures to study the recommenders’ robustness under powerful methods. Letting fixed the perturbation magnitude, we illustrate that MSAP is much more harmful than FGSM in corrupting the recommendation performance of BPR-MF.
Language: Python - Size: 51.9 MB - Last synced at: about 1 year ago - Pushed at: over 2 years ago - Stars: 1 - Forks: 4
