Byzantine machine learning: A primer
The problem of Byzantine resilience in distributed machine learning, aka Byzantine machine
learning, consists of designing distributed algorithms that can train an accurate model …
learning, consists of designing distributed algorithms that can train an accurate model …
Private and reliable neural network inference
Reliable neural networks (NNs) provide important inference-time reliability guarantees such
as fairness and robustness. Complementarily, privacy-preserving NN inference protects the …
as fairness and robustness. Complementarily, privacy-preserving NN inference protects the …
Putting up the swiss army knife of homomorphic calculations by means of TFHE functional bootstrapping
In this work, we first propose a new functional bootstrapping with TFHE for evaluating any
function of domain and codomain the real torus T by using a small number of …
function of domain and codomain the real torus T by using a small number of …
A comprehensive survey and taxonomy on privacy-preserving deep learning
Deep learning (DL) has been shown to be very effective for many application domains of
machine learning (ML), including image classification, voice recognition, natural language …
machine learning (ML), including image classification, voice recognition, natural language …
Combo: A novel functional bootstrapping method for efficient evaluation of nonlinear functions in the encrypted domain
Abstract The application of Fully Homomorphic Encryption (FHE) to privacy issues arising in
inference or training of neural networks has been actively researched over the last few …
inference or training of neural networks has been actively researched over the last few …
A probabilistic design for practical homomorphic majority voting with intrinsic differential privacy
As machine learning (ML) has become pervasive throughout various fields (industry,
healthcare, social networks), privacy concerns regarding the data used for its training have …
healthcare, social networks), privacy concerns regarding the data used for its training have …
Practical homomorphic aggregation for byzantine ml
Due to the large-scale availability of data, machine learning (ML) algorithms are being
deployed in distributed topologies, where different nodes collaborate to train ML models …
deployed in distributed topologies, where different nodes collaborate to train ML models …
Combining homomorphic encryption and differential privacy in federated learning
Recent works have investigated the relevance and practicality of using techniques such as
Differential Privacy (DP) or Homomorphic Encryption (HE) to strengthen training data privacy …
Differential Privacy (DP) or Homomorphic Encryption (HE) to strengthen training data privacy …
Efficient and accurate homomorphic comparisons
O Chakraborty, M Zuber - Proceedings of the 10th Workshop on …, 2022 - dl.acm.org
We design and implement a new efficient and accurate fully homomorphic argmin/min or
argmax/max comparison operator, which finds its application in numerous real-world use …
argmax/max comparison operator, which finds its application in numerous real-world use …
Privacy-Enhanced Knowledge Transfer with Collaborative Split Learning over Teacher Ensembles
Knowledge Transfer has received much attention for its ability to transfer knowledge, rather
than data, from one application task to another. In order to comply with the stringent data …
than data, from one application task to another. In order to comply with the stringent data …