Range-Arithmetic verifies outsourced DNN inference by checking matrix multiplication with sum-check and handling fixed-point rounding and ReLU with Bulletproofs range proofs, achieving logarithmic communication and quadratic verifier work.
Accountable magic: Ai alignment and governance, 2025
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.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
\texttt{Range-Arithmetic}: Verifiable Deep Learning Inference on an Untrusted Party
Range-Arithmetic verifies outsourced DNN inference by checking matrix multiplication with sum-check and handling fixed-point rounding and ReLU with Bulletproofs range proofs, achieving logarithmic communication and quadratic verifier work.