Intercepting intermediate features in split neural network inference lets black-box attackers build surrogate models whose adversarial examples transfer to the target far more often, e.g., 96% versus 61% success in one setting.
Evasion attacks against machine learning at test time
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Exploiting Edge Features for Transferable Adversarial Attacks in Distributed Machine Learning
Intercepting intermediate features in split neural network inference lets black-box attackers build surrogate models whose adversarial examples transfer to the target far more often, e.g., 96% versus 61% success in one setting.