English
Related papers

Related papers: Sisyphus: A Cautionary Tale of Using Low-Degree Po…

200 papers

Outsourcing deep neural networks (DNNs) inference tasks to an untrusted cloud raises data privacy and integrity concerns. While there are many techniques to ensure privacy and integrity for polynomial-based computations, DNNs involve…

Machine Learning · Computer Science 2024-02-07 Ramy E. Ali , Jinhyun So , A. Salman Avestimehr

Private computation of nonlinear functions, such as Rectified Linear Units (ReLUs) and max-pooling operations, in deep neural networks (DNNs) poses significant challenges in terms of storage, bandwidth, and time consumption. To address…

Machine Learning · Computer Science 2023-12-27 Toluwani Aremu

Private Inference (PI) uses cryptographic primitives to perform privacy preserving machine learning. In this setting, the owner of the network runs inference on the data of the client without learning anything about the data and without…

Machine Learning · Computer Science 2025-12-22 Yonathan Bornfeld , Shai Avidan

Private inference (PI) enables inference directly on cryptographically secure data.While promising to address many privacy issues, it has seen limited use due to extreme runtimes. Unlike plaintext inference, where latency is dominated by…

Cryptography and Security · Computer Science 2022-06-09 Minsu Cho , Ameya Joshi , Siddharth Garg , Brandon Reagen , Chinmay Hegde

Private Inference (PI) enables deep neural networks (DNNs) to work on private data without leaking sensitive information by exploiting cryptographic primitives such as multi-party computation (MPC) and homomorphic encryption (HE). However,…

Machine Learning · Computer Science 2024-03-14 Jiajie Li , Jinjun Xiong

The emergence of deep learning has been accompanied by privacy concerns surrounding users' data and service providers' models. We focus on private inference (PI), where the goal is to perform inference on a user's data sample using a…

Cryptography and Security · Computer Science 2022-11-08 Minsu Cho , Zahra Ghodsi , Brandon Reagen , Siddharth Garg , Chinmay Hegde

Hybrid private inference (PI) protocol, which synergistically utilizes both multi-party computation (MPC) and homomorphic encryption, is one of the most prominent techniques for PI. However, even the state-of-the-art PI protocols are…

Cryptography and Security · Computer Science 2022-02-21 Jaiyoung Park , Michael Jaemin Kim , Wonkyung Jung , Jung Ho Ahn

Machine learning as a service has given raise to privacy concerns surrounding clients' data and providers' models and has catalyzed research in private inference (PI): methods to process inferences without disclosing inputs. Recently,…

Machine Learning · Computer Science 2021-05-14 Zahra Ghodsi , Akshaj Veldanda , Brandon Reagen , Siddharth Garg

The recent rise of privacy concerns has led researchers to devise methods for private neural inference -- where inferences are made directly on encrypted data, never seeing inputs. The primary challenge facing private inference is that…

Machine Learning · Computer Science 2021-06-23 Nandan Kumar Jha , Zahra Ghodsi , Siddharth Garg , Brandon Reagen

Rectified Linear Units (ReLUs) are among the most widely used activation function in a broad variety of tasks in vision. Recent theoretical results suggest that despite their excellent practical performance, in various cases, a substitution…

Machine Learning · Computer Science 2020-04-01 Vishnu Suresh Lokhande , Songwong Tasneeyapant , Abhay Venkatesh , Sathya N. Ravi , Vikas Singh

Prior work on Private Inference (PI) -- inferences performed directly on encrypted input -- has focused on minimizing a network's ReLUs, which have been assumed to dominate PI latency rather than FLOPs. Recent work has shown that FLOPs for…

Cryptography and Security · Computer Science 2024-06-25 Nandan Kumar Jha , Brandon Reagen

The privacy concerns of providing deep learning inference as a service have underscored the need for private inference (PI) protocols that protect users' data and the service provider's model using cryptographic methods. Recently proposed…

Cryptography and Security · Computer Science 2022-07-19 Karthik Garimella , Nandan Kumar Jha , Zahra Ghodsi , Siddharth Garg , Brandon Reagen

As privacy concerns in AI technologies continue to grow, Homomorphic Encryption (HE) offers a way to perform computations on encrypted data without the need of decryption during operations. However, HE is limited to addition and…

Cryptography and Security · Computer Science 2026-05-25 Dimitrios Sygletos , Dimitra Papatsaroucha , Marios Choudetsanakis , Ilias Politis , Evangelos K. Markakis

Private inference (PI) serves an important role in guaranteeing the privacy of user data when interfacing with proprietary machine learning models such as LLMs. However, PI remains practically intractable due to the massive latency costs…

Cryptography and Security · Computer Science 2024-12-03 Patrick Yubeaton , Jianqiao Cambridge Mo , Karthik Garimella , Nandan Kumar Jha , Brandon Reagen , Chinmay Hegde , Siddharth Garg

The simultaneous rise of machine learning as a service and concerns over user privacy have increasingly motivated the need for private inference (PI). While recent work demonstrates PI is possible using cryptographic primitives, the…

Machine Learning · Computer Science 2021-06-17 Zahra Ghodsi , Nandan Kumar Jha , Brandon Reagen , Siddharth Garg

Recent work using Fully Homomorphic Encryption (FHE) has made non-interactive privacy-preserving inference of deep Convolutional Neural Networks (CNN) possible. However, the performance of these methods remain limited by their heavy…

Cryptography and Security · Computer Science 2026-02-10 Eduardo Chielle , Manaar Alam , Jinting Liu , Jovan Kascelan , Michail Maniatakos

Ensuring privacy-preserving inference on cryptographically secure data is a well-known computational challenge. To alleviate the bottleneck of costly cryptographic computations in non-linear activations, recent methods have suggested…

Machine Learning · Computer Science 2024-08-21 Saswat Das , Marco Romanelli , Ferdinando Fioretto

The large number of ReLU non-linearity operations in existing deep neural networks makes them ill-suited for latency-efficient private inference (PI). Existing techniques to reduce ReLU operations often involve manual effort and sacrifice…

Computer Vision and Pattern Recognition · Computer Science 2023-01-24 Souvik Kundu , Shunlin Lu , Yuke Zhang , Jacqueline Liu , Peter A. Beerel

Privacy-Preserving Machine Learning algorithms must balance classification accuracy with data privacy. This can be done using a combination of cryptographic and machine learning tools such as Convolutional Neural Networks (CNN). CNNs…

Computer Vision and Pattern Recognition · Computer Science 2021-01-29 Inbar Helbitz , Shai Avidan

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…

Cryptography and Security · Computer Science 2021-10-13 Jiaxiang Liu , Simon Oya , Florian Kerschbaum
‹ Prev 1 2 3 10 Next ›