paper-with-me

Papers

Efficient Skip Connections Realization for Secure Inference on Encrypted Data

2023-06-11 · Nir Drucker, Itamar Zimerman

Homomorphic Encryption (HE) is a cryptographic tool that allows performing computation under encryption, which is used by many privacy-preserving machine learning solutions, for example, to perform secure classification. Modern deep learning applications yield good performance for example in image processing tasks benchmarks by including many skip connections. The latter appears to be very costly when attempting to execute model inference under HE. In this paper, we show that by replacing (mid-term) skip connections with (short-term) Dirac parameterization and (long-term) shared-source skip connection we were able to reduce the skip connections burden for HE-based solutions, achieving x1.3 computing power improvement for the same accuracy.

📄 PDF Abstract BibTeX arXiv:2306.06736

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preserving

Similar Papers 제목 키워드 기반

SecureRouter: Encrypted Routing for Efficient Secure Inference

2026-04-16 · Yukuan Zhang, Mengxin Zheng, Qian Lou arxiv

Cryptographically secure neural network inference typically relies on secure computing techniques such as Secure Multi-Party Computation (MPC), enabling cloud servers to process client inputs without decrypting them. Alt…

Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption

2023-04-26 · Moran Baruch, Nir Drucker, Gilad Ezov, Yoav Goldberg 외

Training large-scale CNNs that during inference can be run under Homomorphic Encryption (HE) is challenging due to the need to use only polynomial operations. This limits HE-based solutions adoption. We address this chal…

Privacy PreservingTransfer Learning

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets

2020-02-14 · ICLR 2020 1 · Dongxian Wu, Yisen Wang, Shu-Tao Xia, James Bailey 외

Skip connections are an essential component of current state-of-the-art deep neural networks (DNNs) such as ResNet, WideResNet, DenseNet, and ResNeXt. Despite their huge success in building deeper and more powerful DNNs,…

Reverse Delegated Training and Private Inference via Perfectly-Secure Quantum Homomorphic Encryption

2026-02-13 · Sergio A. Ortega, Miguel A. Martin-Delgado arxiv

Quantum machine learning in cloud environments requires protecting sensitive data while enabling remote computation. Here we demonstrate the first realistic implementations of a perfectly-secure quantum homomorphic encry…

Quantum Machine Learning

Towards Provably Secure Encrypted Control Using Homomorphic Encryption

2022-10-17 · Kaoru Teranishi, Kiminao Kogiso

Encrypted control is a promising method for the secure outsourcing of controller computation to a public cloud. However, a feasible method for security proofs of control has not yet been developed in the field of encrypt…

Mathematical Proofs