LAUSR

Stealthy Query-Efficient OpaqueAttack Against Interpretable Deep Learning

Sign Up to like & get
recommendations!
0 Published in 2025 at "IEEE Transactions on Reliability"

DOI: 10.1109/tr.2025.3551717

Abstract: Deep neural network (DNN) models are susceptible to adversarial samples in white-box and opaqueenvironments. Although previous studies have shown high attack success rates, coupling DNN models with interpretation models could offer a sense of security… read more here.

Keywords: interpretable deep; deep learning; stealthy query; attack ... See more keywords