Privacy-preserving machine learning: Methods, challenges and directions
Machine learning (ML) is increasingly being adopted in a wide variety of application
domains. Usually, a well-performing ML model relies on a large volume of training data and …
domains. Usually, a well-performing ML model relies on a large volume of training data and …
Layered obfuscation: a taxonomy of software obfuscation techniques for layered security
Software obfuscation has been developed for over 30 years. A problem always confusing
the communities is what security strength the technique can achieve. Nowadays, this …
the communities is what security strength the technique can achieve. Nowadays, this …
Leakage-abuse attacks against order-revealing encryption
Order-preserving encryption and its generalization order-revealing encryption (OPE/ORE)
allow sorting, performing range queries, and filtering data-all while only having access to …
allow sorting, performing range queries, and filtering data-all while only having access to …
Iron: functional encryption using Intel SGX
B Fisch, D Vinayagamurthy, D Boneh… - Proceedings of the 2017 …, 2017 - dl.acm.org
Functional encryption (FE) is an extremely powerful cryptographic mechanism that lets an
authorized entity compute on encrypted data, and learn the results in the clear. However, all …
authorized entity compute on encrypted data, and learn the results in the clear. However, all …
Cryptonn: Training neural networks over encrypted data
Emerging neural networks based machine learning techniques such as deep learning and
its variants have shown tremendous potential in many application domains. However, they …
its variants have shown tremendous potential in many application domains. However, they …
Raziel: Private and verifiable smart contracts on blockchains
DC Sánchez - arXiv preprint arXiv:1807.09484, 2018 - arxiv.org
Raziel combines secure multi-party computation and proof-carrying code to provide privacy,
correctness and verifiability guarantees for smart contracts on blockchains. Effectively …
correctness and verifiability guarantees for smart contracts on blockchains. Effectively …
Lattice-based SNARGs and their application to more efficient obfuscation
Succinct non-interactive arguments (SNARGs) enable verifying NP computations with
substantially lower complexity than that required for classical NP verification. In this work, we …
substantially lower complexity than that required for classical NP verification. In this work, we …
NN-EMD: Efficiently Training Neural Networks Using Encrypted Multi-Sourced Datasets
Training complex neural network models using third-party cloud-based infrastructure among
multiple data sources is a promising approach among existing machine learning solutions …
multiple data sources is a promising approach among existing machine learning solutions …
Giving state to the stateless: Augmenting trustworthy computation with ledgers
In this work we investigate the problem of achieving secure computation by combining
stateless trusted devices with public ledgers. We consider a hybrid paradigm in which a …
stateless trusted devices with public ledgers. We consider a hybrid paradigm in which a …
[PDF][PDF] HOP: Hardware makes Obfuscation Practical.
Program obfuscation is a central primitive in cryptography, and has important real-world
applications in protecting software from IP theft. However, well known results from the …
applications in protecting software from IP theft. However, well known results from the …