Related papers: Aggregation and Embedding for Group Membership Ver…

Recently, a quantum multi-party summation protocol based on the quantum Fourier transform has been proposed [Quantum Inf Process 17: 129, 2018]. The protocol claims to be secure against both outside and participant attacks. However, a…

Secure aggregation enables aggregation of inputs from multiple parties without revealing individual contributions to the server or other clients. Existing post-quantum approaches based on homomorphic encryption offer practical efficiency…

Federated learning is a computing paradigm that enhances privacy by enabling multiple parties to collaboratively train a machine learning model without revealing personal data. However, current research indicates that traditional federated…

We consider the problem of estimating community memberships of nodes in a network, where every node is associated with a vector determining its degree of membership in each community. Existing provably consistent algorithms often require…

Protecting privacy in social graphs may require obscuring nodes' membership in sensitive communities. However, doing so without significantly disrupting the underlying graph topology remains a key challenge. In this work, we address the…

This paper introduces a refined graph encoder embedding method, enhancing the original graph encoder embedding through linear transformation, self-training, and hidden community recovery within observed communities. We provide the…

Recent secure aggregation protocols enable privacy-preserving federated learning for high-dimensional models among thousands or even millions of participants. Due to the scale of these use cases, however, end-to-end empirical evaluation of…

Aggregation of values that need to be kept confidential while guaranteeing the robustness of the process and the correctness of the result is required in an increasing number of applications. We propose an aggregation algorithm, which…

Community detection techniques are useful for social media platforms to discover tightly connected groups of users who share common interests. However, this functionality often comes at the expense of potentially exposing individuals to…

This paper suggests a message authentication scheme, which can be efficiently used for secure digital signature creation. The algorithm used here is an adjusted union of the concepts which underlie projective geometry and group structure on…

In this work, we study interception attacks against a secret sharing protocol based on Grovers search algorithm. Unlike previous works that only give the algorithm for two and three participants, we have generalized the algorithm for any…

Private handshaking allows pairs of users to determine which (secret) groups they are both a member of. Group membership is kept secret to everybody else. Private handshaking is a more private form of secret handshaking, because it does not…

This paper presents a secure aggregation system Armadillo that has disruptive resistance against adversarial clients, such that any coalition of malicious clients (within the tolerated threshold) can affect the aggregation result only by…

This paper presents an algorithm for enumerating biases in word embeddings. The algorithm exposes a large number of offensive associations related to sensitive features such as race and gender on publicly available embeddings, including a…

Text embeddings are fundamental to many natural language processing (NLP) tasks, extensively applied in domains such as recommendation systems and information retrieval (IR). Traditionally, transmitting embeddings instead of raw text has…

For collaborative inference through a cloud computing platform, it is sometimes essential for the client to shield its sensitive information from the cloud provider. In this paper, we introduce Ensembler, an extensible framework designed to…

The Gaussian mixture model is widely used in unsupervised learning, owing to its simplicity and interpretability. However, a fundamental limitation of the classical Gaussian mixture model is that it forces each observation to belong to…

Federated learning has been proposed as a privacy-preserving machine learning framework that enables multiple clients to collaborate without sharing raw data. However, client privacy protection is not guaranteed by design in this framework.…

The trade-off of secrecy is the difficulty of verification. This trade-off means that contracts must be kept private, yet their compliance needs to be verified, which we call the secrecy-verifiability paradox. However, the existing smart…

Graph embedding technics are studied with interest on public datasets, such as BlogCatalog, with the common practice of maximizing scoring on graph reconstruction, link prediction metrics etc. However, in the financial sector the important…