Randomly composing multiple trained parameter versions per layer reduces side-channel leakage on an unmodified Edge TPU, though detectable leakage remains.
The security of machine learning in an adversarial setting: A survey,
1 Pith paper cite this work, alongside 200 external citations. Polarity classification is still indexing.
1
Pith paper citing it
200
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
No TPU Left Behind: Retrofitting Side-Channel Protection into Edge TPUs
Randomly composing multiple trained parameter versions per layer reduces side-channel leakage on an unmodified Edge TPU, though detectable leakage remains.