all InfoSec news
Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection. (arXiv:2302.03857v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
Adversarial contrastive learning (ACL) does not require expensive data
annotations but outputs a robust representation that withstands adversarial
attacks and also generalizes to a wide range of downstream tasks. However, ACL
needs tremendous running time to generate the adversarial variants of all
training data, which limits its scalability to large datasets. To speed up ACL,
this paper proposes a robustness-aware coreset selection (RCS) method. RCS does
not require label information and searches for an informative subset that
minimizes a representational …
acl adversarial adversarial attacks attacks aware data datasets information large rcs representation robustness scalability speed speed up training