The paper identifies a simple undetectable model-stealing attack in multikey encrypted ML inference and proposes a verification-slot protocol that, as described, reveals the verification slot positions to the client, undermining its own security claim.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SONNI: Secure Oblivious Neural Network Inference
The paper identifies a simple undetectable model-stealing attack in multikey encrypted ML inference and proposes a verification-slot protocol that, as described, reveals the verification slot positions to the client, undermining its own security claim.