Scaling up Trustless DNN Inference with Zero-Knowledge Proofs

The use of confidence or fiducial limits illustrated in the case of the binomial

Clopper, C. J. and Pearson, E. S · 1934

Earlier work this paper cites.

A method for obtaining digital signatures and public-key cryptosystems

Rivest, R. L., Shamir, A., and Adleman, L · 1978

Earlier work this paper cites.

Cryptographic hash-function basics: Definitions, implications, and separations for preimage resistance, second-preimage resistance, and collision resistance

Rogaway, P. and Shrimpton, T · 2004

Earlier work this paper cites.

Quadratic span programs and succinct nizks without pcps

Gennaro, R., Gentry, C., Parno, B., and Raykova, M · 2013

Earlier work this paper cites.

Time-optimal interactive proofs for circuit evaluation

Thaler, J · 2013

Earlier work this paper cites.

A guide to fully homomorphic encryption

Armknecht, F., Boyd, C., Carr, C., Gjøsteen, K., Jäschke, A., Reuter, C. A., and Strand, M · 2015

Earlier work this paper cites.

Interactive oracle proofs

Ben-Sasson, E., Chiesa, A., and Spooner, N · 2016

Earlier work this paper cites.

On the size of pairing-based non-interactive arguments

Groth, J · 2016

Earlier work this paper cites.

The hunting of the snark

Bitansky, N., Canetti, R., Chiesa, A., Goldwasser, S., Lin, H., Rubinstein, A., and Tromer, E · 2017

Earlier work this paper cites.

Secureml: A system for scalable privacy-preserving machine learning

Mohassel, P. and Zhang, Y · 2017

Earlier work this paper cites.

Scalable, transparent, and post-quantum secure computational integrity

Ben-Sasson, E., Bentov, I., Horesh, Y., and Riabzev, M · 2018

Earlier work this paper cites.

{ \{ GAZELLE } \} : A low latency framework for secure neural network inference

Juvekar, C., Vaikuntanathan, V., and Chandrakasan, A · 2018

Earlier work this paper cites.

Mobilenetv2: Inverted residuals and linear bottlenecks

Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C · 2018

Cited alongside, same era.

Tf-slim: A high level library to define complex models in tensorflow, 2018

Silberman, N. and Guadarrama, S · 2018

Cited alongside, same era.

Recursive proof composition without a trusted setup

Bowe, S., Grigg, J., and Hopwood, D · 2019

Cited alongside, same era.

Plonk: Permutations over lagrange-bases for oecumenical noninteractive arguments of knowledge

Gabizon, A., Williamson, Z. J., and Ciobotaru, O · 2019

Cited alongside, same era.

Poseidon: A new hash function for zero-knowledge proof systems

Grassi, L., Khovratovich, D., Rechberger, C., Roy, A., and Schofnegger, M · 2019

Cited alongside, same era.

The cost of machine learning projects

Incze, R · 2019

Cited alongside, same era.

From airs to raps - how plonk-style arithmetization works

Gabizon, A · 2021

Later among the works it cites.

Deepreduce: Relu reduction for fast private inference

Jha, N. K., Ghodsi, Z., Garg, S., and Reagen, B · 2021

Later among the works it cites.

Crypten: Secure multi-party computation meets machine learning

Knott, B., Venkataraman, S., Hannun, A., Sengupta, S., Ibrahim, M., and van der Maaten, L · 2021

Later among the works it cites.

Zkcnn: Zero knowledge proofs for convolutional neural network predictions and accuracy

Liu, T., Xie, X., and Zhang, Y · 2021

Later among the works it cites.

Hemet: A homomorphic-encryption-friendly privacy-preserving mobile neural network architecture

Lou, Q. and Jiang, L · 2021

Later among the works it cites.

Privacy-preserving video classification with convolutional neural networks

Pentyala, S., Dowsley, R., and De Cock, M · 2021