REVIEW 8 cited by
TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Machine learning algorithms have achieved remarkable results and are widely applied in a variety of domains. These algorithms often rely on sensitive and private data such as medical and financial records. Therefore, it is vital to draw further attention regarding privacy threats and corresponding defensive techniques applied to machine learning models. In this paper, we present TenSEAL, an open-source library for Privacy-Preserving Machine Learning using Homomorphic Encryption that can be easily integrated within popular machine learning frameworks. We benchmark our implementation using MNIST and show that an encrypted convolutional neural network can be evaluated in less than a second, using less than half a megabyte of communication.
Forward citations
Cited by 8 Pith papers
-
Federated Learning: An approach with Hybrid Homomorphic Encryption
Pairing the PASTA stream cipher with BFV homomorphic encryption in federated learning cuts client upload by about 2000x and keeps MNIST accuracy within 1.3% of plaintext, but makes server aggregation roughly 15,000x m...
-
HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption
Client-side digit decomposition and block-diagonal packing enable server-side private embedding lookups in FHE, cutting embedding-lookup latency by up to 56x versus CodedHeLUT and enabling end-to-end encrypted DLRM in...
-
Safety and Security: Experimental Validation of Encrypted Model Predictive Control
An explicit MPC controller is replaced by a polynomial, encrypted with BFV homomorphic encryption, and run on a lab device; the demo works, but the claimed stability guarantee relies on an invalid error bound.
-
Adaptive Federated Learning to Optimize Integrated Flows in Cyber-Physical Data Centers
An adaptive federated learning-to-optimization method with a rejection-capable acceptance rule and verifiable double aggregation achieves near-centralized cost for data center energy management without exposing local data.
-
HyFedRAG: A Federated Retrieval-Augmented Generation Framework for Heterogeneous and Privacy-Sensitive Data
HyFedRAG is a federated RAG framework over heterogeneous data with local anonymization and three-tier caching, but the experiments do not support its headline performance and privacy claims.
-
Efficient Privacy-Preserving Recommendation on Sparse Data using Fully Homomorphic Encryption
Encrypted matrix factorization using Compressed Sparse Row representation and CKKS fully homomorphic encryption is claimed to reduce communication cost to M/L ciphertexts while keeping accuracy, but the evaluation lac...
-
Secure Distributed Learning for CAVs: Defending Against Gradient Leakage with Leveled Homomorphic Encryption
The paper claims CKKS-based selective encryption can protect federated learning from gradient leakage while preserving accuracy, but it never runs a leakage attack and gives the server the decryption key.
-
Technical Evaluation of a Disruptive Approach in Homomorphic AI
A self-evaluation by the scheme's co-designer of a black-box 'homomorphic AI' hash reports perfect clustering on one dataset but degraded off-the-shelf accuracy on Fashion-MNIST, improved only after custom post-hoc tuning.
Discussion (0). Sign in to comment.