all InfoSec news
Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend. (arXiv:2305.10766v1 [cs.AI])
cs.CR updates on arXiv.org arxiv.org
Adversarial attack is commonly regarded as a huge threat to neural networks
because of misleading behavior. This paper presents an opposite perspective:
adversarial attacks can be harnessed to improve neural models if amended
correctly. Unlike traditional adversarial defense or adversarial training
schemes that aim to improve the adversarial robustness, the proposed
adversarial amendment (AdvAmd) method aims to improve the original accuracy
level of neural models on benign samples. We thoroughly analyze the
distribution mismatch between the benign and adversarial samples. …
adversarial adversarial attacks aim attack attacks defense networks neural networks perspective threat training