Unbiased gradient extraction for attacking quantum classifiers costs at least Θ(d^{5/2}) shots under norm-concentration scaling, and ~d³ for tested deep circuits, so the attacker's relative cost diverges versus classical models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When cheap gradients fail: the measurement cost of attacking quantum classifiers
Unbiased gradient extraction for attacking quantum classifiers costs at least Θ(d^{5/2}) shots under norm-concentration scaling, and ~d³ for tested deep circuits, so the attacker's relative cost diverges versus classical models.