Transferability of features for neural networks links to adversarial attacks and defences
Sign Up to like & getrecommendations! Published in 2022 at "PLoS ONE"
DOI: 10.1371/journal.pone.0266060
Abstract: The reason for the existence of adversarial samples is still barely understood. Here, we explore the transferability of learned features to Out-of-Distribution (OoD) classes. We do this by assessing neural networks’ capability to encode the… read more here.
Keywords: adversarial attacks; neural networks; ood classes; attacks defences ... See more keywords