Robustness to adversarial examples can be improved with overfitting
Sign Up to like & getrecommendations! Published in 2020 at "International Journal of Machine Learning and Cybernetics"
DOI: 10.1007/s13042-020-01097-4
Abstract: Deep learning (henceforth DL) has become most powerful machine learning methodology. Under specific circumstances recognition rates even surpass those obtained by humans. Despite this, several works have shown that deep learning produces outputs that are… read more here.
Keywords: robustness adversarial; machine learning; improved overfitting; adversarial examples ... See more keywords