Inserting SWAP gates into the variational circuit of a hybrid quantum neural network degrades classification accuracy by up to roughly 74%, with targeted insertions able to ruin a single class's accuracy.
Hybrid quantum–classical convolutional neural networks with privacy quantum computing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SQUASH: A SWAP-Based Quantum Attack to Sabotage Hybrid Quantum Neural Networks
Inserting SWAP gates into the variational circuit of a hybrid quantum neural network degrades classification accuracy by up to roughly 74%, with targeted insertions able to ruin a single class's accuracy.