Related papers: Towards Anonymous Neural Network Inference

Machine learning models are increasingly used in societal applications, yet legal and privacy concerns demand that they very often be kept confidential. Consequently, there is a growing distrust about the fairness properties of these models…

We propose AriaNN, a low-interaction privacy-preserving framework for private neural network training and inference on sensitive data. Our semi-honest 2-party computation protocol (with a trusted dealer) leverages function secret sharing, a…

Large scale deep learning model, such as modern language models and diffusion architectures, have revolutionized applications ranging from natural language processing to computer vision. However, their deployment in distributed or…

We present Chameleon, a novel hybrid (mixed-protocol) framework for secure function evaluation (SFE) which enables two parties to jointly compute a function without disclosing their private inputs. Chameleon combines the best aspects of…

In today's digital age, personal data is constantly at risk of compromise. Attribute-Based Encryption (ABE) has emerged as a promising approach to privacy-preserving data protection. This paper proposes an anonymous authentication mechanism…

Resilience against malicious participants and data privacy are essential for trustworthy federated learning, yet achieving both with good utility typically requires the strong assumption of a trusted central server. This paper shows that a…

As more and more data is transmitted in the configurable optical layer, whereby all optical switches forward packets without electronic layers involved, we envision privacy as the intrinsic property of future optical networks. In this…

In this paper, a secure Convolutional Neural Network classifier is proposed using Fully Homomorphic Encryption (FHE). The secure classifier provides a user with the ability to out-source the computations to a powerful cloud server and/or…

Today's cloud vendors are competing to provide various offerings to simplify and accelerate AI service deployment. However, cloud users always have concerns about the confidentiality of their runtime data, which are supposed to be processed…

Federated learning (FL) is a distributed machine learning paradigm enabling multiple clients to train a model collaboratively without exposing their local data. Among FL schemes, clustering is an effective technique addressing the…

Obtaining and maintaining anonymity on the Internet is challenging. The state of the art in deployed tools, such as Tor, uses onion routing (OR) to relay encrypted connections on a detour passing through randomly chosen relays scattered…

Over the past decade, the Bitcoin P2P network protocol has become a reference model for all modern cryptocurrencies. While nodes in this network are known, the connections among them are kept hidden, as it is commonly believed that this…

Recently, deep learning, which uses Deep Neural Networks (DNN), plays an important role in many fields. A secure neural network model with a secure training/inference scheme is indispensable to many applications. To accomplish such a task…

Process anonymity has been studied for a long time. Memory anonymity is more recent. In an anonymous memory system, there is no a priori agreement among the processes on the names of the shared registers they access. This article introduces…

Secure aggregation of high-dimensional vectors is a fundamental primitive in federated statistics and learning. A two-server system such as PRIO allows for scalable aggregation of secret-shared vectors. Adversarial clients might try to…

A privacy-preserving framework in which a computational resource provider receives encrypted data from a client and returns prediction results without decrypting the data, i.e., oblivious neural network or encrypted prediction, has been…

Recent advances in programmable switch hardware offer a fresh opportunity to protect user privacy. This paper presents PINOT, a lightweight in-network anonymity solution that runs at line rate within the memory and processing constraints of…

Growing concern for individual privacy, driven by an increased public awareness of the degree to which many of our electronic activities are tracked by interested third parties (e.g. Google knows what I am thinking before I finish entering…

Vehicular Ad Hoc Networks (VANETs) are attractive scenarios that can improve the traffic situation and provide convenient services for drivers and passengers via vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication.…

Many anonymous communication (AC) networks rely on routing traffic through proxy nodes to obfuscate the originator of the traffic. Without an accountability mechanism, exit proxy nodes risk sanctions by law enforcement if users commit…