Veriml: Enabling integrity assurances and fair payments for machine learning as a service

L Zhao, Q Wang, C Wang, Q Li… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Machine Learning as a Service (MLaaS) allows clients with limited resources to outsource
their expensive ML tasks to powerful servers. Despite the huge benefits, current MLaaS …

Efficient secure and verifiable outsourcing of matrix multiplications

Y Zhang, M Blanton - International Conference on Information Security, 2014 - Springer
With the emergence of cloud computing services, a resource-constrained client can
outsource its computationally-heavy tasks to cloud providers. Because such service …

Towards attack and defense views of rational delegation of computation

Y Tian, J Guo, Y Wu, H Lin - IEEE Access, 2019 - ieeexplore.ieee.org
Rational delegation of computation is an important technology of mobile Internet at present,
which is significant to the construction of intelligent urban computing. In order to close to …

Super-efficient rational proofs

PD Azar, S Micali - Proceedings of the fourteenth ACM conference on …, 2013 - dl.acm.org
Information asymmetry is a central problem in both computer science and economics. In
many fundamental problems, an uninformed principal wants to obtain some knowledge from …

Rational arguments: single round delegation with sublinear verification

S Guo, P Hubáček, A Rosen, M Vald - Proceedings of the 5th …, 2014 - dl.acm.org
Rational proofs, recently introduced by Azar and Micali (STOC 2012), are a variant of
interactive proofs in which the prover is neither honest nor malicious, but rather rational. The …

Rational sumchecks

S Guo, P Hubáček, A Rosen, M Vald - Theory of Cryptography Conference, 2015 - Springer
Rational proofs, introduced by Azar and Micali (STOC 2012) are a variant of interactive
proofs in which the prover is neither honest nor malicious, but rather rational. The advantage …

Rational proofs with multiple provers

J Chen, S McCauley, S Singh - … of the 2016 ACM Conference on …, 2016 - dl.acm.org
Interactive proofs model a world where a verifier delegates computation to an untrustworthy
prover, verifying the prover's claims before accepting them. These proofs have applications …

Fine-grained secure computation

M Campanelli, R Gennaro - Theory of Cryptography Conference, 2018 - Springer
This paper initiates a study of Fine Grained Secure Computation: ie the construction of
secure computation primitives against “moderately complex” adversaries. We present …

Smart contracts meet quantum cryptography

A Coladangelo - arXiv preprint arXiv:1902.05214, 2019 - arxiv.org
We put forward the idea that classical blockchains and smart contracts are potentially useful
primitives not only for classical cryptography, but for quantum cryptography as well …

Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness

M Ehrenberg, R Ganz, N Rosenfeld - arXiv preprint arXiv:2406.11458, 2024 - arxiv.org
Adversarial training aims to defend against* adversaries*: malicious opponents whose sole
aim is to harm predictive performance in any way possible-a rather harsh perspective, which …