Relying solely on encryption for privacy-preserving computations is prone to leakage-abuse/access-pattern attacks. TEEs, while cost-effective, are also vulnerable to side-channel attacks. Oblivious primitives, such as oblivious memory (ORAM) and data structures (ODS), are effective building blocks to mitigate these risks by concealing memory access patterns and side-channel information. Applications range from private contact discovery (Signal) to anonymous key transparency, encrypted email...

PRIVIDEMA project (Privacy-Preserving Identity Management for Digital Wallets and Secure Data Sharing and Processing for Cyber Threat Intelligence Data) advances the state of the art in cryptographic and Privacy-Enhancing Technologies (PETs) to enable secure, interoperable, and trustworthy data exchange across sectors, with a focus on the domains of Cyber Threat Intelligence and Digital Identity Management. This paper presents two representative real-world use-cases: (1)...

As the usage of Artificial Intelligence (AI) for sensitive purposes increases, there is a growing need for privacy-aware explainable AI (XAI) tools. In this paper, we present a privacy-preserving counterfactual explanation algorithm. Our starting point is a decision-support model that is able to operate on vertically partitioned datasets, meaning that each party holds a different subset of datapoint attributes. The goal of a counterfactual algorithm is to find, given an observation, a...

Federated Learning (FL) enables collaborative model training without centralizing raw data, but remains vulnerable to gradient inference attacks, malicious aggregation servers, and communication inefficiencies. Existing cryptographic secure aggregation schemes provide confidentiality and verifiability yet lack formal statistical privacy guarantees, while most differential privacy (DP)-based approaches rely on fixed noise injection, resulting in suboptimal privacy--utility tradeoffs. This...

We introduce Falafel, a modular scheme for Fast, Authenticated, Locally Attested FEderated Learning, with which parties can create a zero-knowledge proof of training (zkPoT) for Federated Learning (FL). The proof guarantees active security during the federated training process as well as publicly verifiable correctness of the final, trained model. All without revealing any additional information about the local datasets or intermediate local model states. Specifically, our approach...

Ensuring the integrity and traceability of data transformations in distributed systems presents significant challenges, particularly in environments where data privacy and decentralization are paramount. This paper introduces a novel secure lineage verification system based on Directed Acyclic Graphs (DAGs) and homomorphic hash functions, VERDICT. Our approach represents data artifacts and their transformations as two interconnected DAGs: a Data DAG tracking data dependencies and an...

The rapid adoption of blockchain-based financial systems has been accompanied by a surge in illicit activities, including money laundering, ransomware payments, phishing scams, and terrorist financing, necessitating robust anomalous transaction detection mechanisms. Detecting anomalies in cryptocurrency transactions is critical, as undetected illicit activity can result in significant economic losses and undermine trust in digital financial systems. This systematic review examines the...

Trustworthy federated learning requires both update privacy and aggregate integrity. While secure aggregation protects the confidentiality of client updates, it does not prevent a malicious server from tampering with the final aggregate. Existing verifiable schemes typically address this limitation by introducing separate integrity-verification layers, such as zero-knowledge proofs, homomorphic hashes, and commitmentbased mechanisms. However, these approaches either require clients to remain...

In federated learning (FL), secure aggregation (SA) allows a server to compute aggregate model updates (gradients) without accessing individual client gradients. SA is intended to protect clients’ local dataset from being inferred through individual gradients. However, recent NDSS 2025 work shows that even state-of-the-art SA protocols can be vulnerable, as a malicious server may reconstruct clients’ datasets from aggregated gradients. This demonstrates that protecting dataset privacy...

Privacy‑preserving aggregation is a cornerstone for AI systems that learn from distributed data without exposing individual records, especially in federated learning and telemetry. Existing two‑server protocols (e.g., Prio and successors) set a practical baseline by validating inputs while preventing any single party from learning users’ values, but they impose symmetric costs on both servers and communication that scales with the per‑client input dimension $L$. Modern learning tasks...

Stochastic Gradient Descent (SGD) is the foundation of modern machine learning (ML). In privacy-sensitive settings, gradients can reveal details about individual data points. Differential Privacy (DP) protects sensitive data during ML training by clipping gradients and adding calibrated Gaussian noise. However, existing frameworks assume semi-honest participants, which fails in adversarial or federated environments where malicious actors can bypass or alter the noise addition process,...

Privacy-Preserving Federated Learning (PPFL) emphasizes the security and privacy of contributors' data in scenarios such as healthcare, smart grids, and the Internet of Things. However, ensuring the security and privacy throughout PPFL can be challenging, given the complexities of maintaining relationships with many users across multiple epochs. Additionally, under a threat model in which the aggregating server and corrupted users are colluding adversaries, honest users' inputs and output...

The distributed nature of federated learning systems makes them vulnerable to backdoor attacks in which malicious clients manipulate local training data using trigger-dependent behaviors to cause targeted misclassification. Although homomorphic encryption preserves the privacy of model updates during aggregation, it limits the application of conventional defenses that require access to plaintext updates. Moreover, distinguishing poisoned models from benign variations becomes more challenging...

Federated Learning is an emerging machine learning paradigm that enables distributed model training directly at data sources and transmitting only model updates, thereby reducing communication bottlenecks and mitigating risks associated with raw data exposure. Despite these advantages, recent advances have demonstrated that privacy in federated learning remains limited and subject to inference attacks that exploit shared model updates to extract sensitive information. To address this...

Secure aggregation is a core primitive for privacy-preserving federated learning, enabling a server to compute aggregates of client updates without learning individual inputs. Recent protocols have explored committee-based designs to reduce client overhead and tolerate weakly connected participants. However, existing approaches still incur communication and computation costs that scale with the number of clients and/or the size of model updates. This becomes a serious bottleneck in...

Federated Learning (FL) is a collaborative Machine Learning (ML) process where clients locally train an ML model on their private inputs, and send it to a server that aggregates the local model updates to obtain a global model update. FL is widely used in applications where the training data is distributed among several clients, e.g., for next word prediction in Google keyboard (Gboard). Nevertheless, FL faces several challenges concerning privacy and security. 1) Client privacy needs to be...

Differential privacy (DP) has emerged as a rigorous framework for privacy-preserving data analysis, with widespread deployment in industry and government. Yet existing implementations typically assume that the party applying the mechanism can be trusted to sample noise correctly. This trust assumption is overly optimistic: a malicious party may deviate from the protocol to gain accuracy or avoid scrutiny, thereby undermining users’ privacy guarantees. In this paper, we introduce Noisette,...

Federated Learning (FL) is an advancement in Machine Learning motivated by the need to preserve the privacy of the data used to train models. While it effectively addresses this issue, the multi-participant paradigm on which it is based introduces several challenges. Among these are the risks that participating entities may behave dishonestly and fail to perform their tasks correctly. This misbehavior, in turn, also threatens privacy, because an undetected deviation in training or...

We introduce a simple yet novel framework for privacy-preserving machine learning inference that allows a client to query multiple models without a trusted third party aggregator by leveraging homomorphically encrypted model evaluation and multi-party computation. This setting allows for dispersed training of models such that a client can query each separately, and aggregate the results of this `ensemble inference'; this avoids the data leakage inherent to techniques that train collectively...

We present arya-STARK, a unified post-quantum secure framework that enables Aggregation-Robust Yet Authentic training in Federated Learning through transparent zk-STARK proofs. Current federated learning deployments remain vulnerable to malicious or Byzantine clients capable of submitting statistically valid yet adversarial gradients, while also relying on quantum-fragile primitives for authentication. arya-STARK bridges these gaps by combining (i) transparent, hash-based zk-STARK proofs to...

Secure aggregation enables a central server to compute the sum of client inputs without learning any individual input, even in the presence of dropouts or partial participation. This primitive is fundamental to privacy-preserving applications such as federated learning, where clients collaboratively train models without revealing raw data. We present a new secure aggregation protocol, TACITA, in the single-server setting that satisfies four critical properties simultaneously: (1) one-shot...

In recent years, federated learning has gained significant momentum as a collaborative machine learning approach, particularly in the field of medicine. While the decentralized nature of federated learning provides greater security guarantees compared to traditional machine learning methods, it is still susceptible to myriad attacks. Moreover, as federated learning becomes increasingly ubiquitous in medicine, its use for classification tasks is expected to increase; however, maintaining...

Vertical federated learning (VFL) enables a cohort of parties with vertically partitioned data to collaboratively train a machine learning (ML) model without requiring them to centralise their data. Each party feeds its data to its local model, with output fed to a global model. However, this configuration requires parties to share some intermediary results during training, which include the output and the gradients of the local models. These intermediary results can reveal insights into the...

Federated learning (FL) proposes to train a global machine learning model across distributed datasets. However, the aggregation protocol as the core component in FL is vulnerable to well-studied attacks, such as inference attacks, poisoning attacks [71] and malicious participants who try to deviate from the protocol [24]. Therefore, it is crucial to achieve both malicious security and poisoning resilience from cryptographic and FL perspectives, respectively. Prior works either achieve...

In many fields, the need to securely collect and aggregate data from distributed systems is growing. However, designs that rely solely on encrypted data transmission make it difficult to trace malicious users. To address this challenge, we have enhanced the secure aggregation (SA) protocol proposed by Bell et al. (CCS 2020) by introducing verification features that ensure compliance with user inputs and encryption processes while preserving data privacy. We present LZKSA, a quantum-safe...

Federated Learning (FL) allows clients to engage in learning without revealing their raw data. However, traditional FL focuses on developing a single global model for all clients, limiting their ability to have personalized models tailored to their specific needs. Personalized FL (PFL) enables clients to obtain their customized models, either with or without a central party. Current PFL research includes mechanisms to detect poisoning attacks, in which a couple of malicious nodes try to...

Federated Learning (FL) has become a crucial framework for collaboratively training Machine Learning (ML) models while ensuring data privacy. Traditional synchronous FL approaches, however, suffer from delays caused by slower clients (called stragglers), which hinder the overall training process. Specifically, in a synchronous setting, model aggregation happens once all the intended clients have submitted their local updates to the server. To address these inefficiencies, Buffered...

Federated Learning (FL) has emerged as a prominent paradigm for collaborative machine learning that enables model training without exposing private data through data decentralisation. Despite these advantages, FL systems remain vulnerable to significant security challenges affecting both privacy and robustness. This paper examines vulnerabilities in FL with a particular focus on model robustness, identifying critical gaps in existing defences against adaptive adversaries that alter their...

We revisit the problem of secure aggregation of high-dimensional vectors in a two-server system such as Prio. These systems are typically used to aggregate vectors such as gradients in private federated learning, where the aggregate itself is protected via noise addition to ensure differential privacy. Existing approaches require communication scaling with the dimensionality, and thus limit the dimensionality of vectors one can efficiently process in this setup. We propose PREAMBLE:...

We show that the threshold signature scheme [J. Ind. Inf. Integr. 39: 100593 (2024)] is insecure against forgery attack. An adversary can find an efficient signing algorithm functionally equivalent to the valid signing algorithm, so as to convert the legitimate signature $(sig, s, r_x)$ of message $m$ into a valid signature $(sig, s, r_x')$ of any message $m'$.

Generative models have achieved remarkable success in a wide range of applications. Training such models using proprietary data from multiple parties has been studied in the realm of federated learning. Yet recent studies showed that reconstruction of authentic training data can be achieved in such settings. On the other hand, multiparty computation (MPC) guarantees standard data privacy, yet scales poorly for training generative models. In this paper, we focus on improving...

Oblivious Transfer (OT) is a fundamental cryptographic primitive introduced nearly four decades ago. OT allows a receiver to select and learn $t$ out of $n$ private messages held by a sender. It ensures that the sender does not learn which specific messages the receiver has chosen, while the receiver gains no information about the remaining $n − t$ messages. In this work, we introduce the notion of functional OT (FOT), for the first time. FOT adds a layer of security to the conventional OT...

Federated Learning, as a multi-party machine learning paradigm, has garnered significant attention, but model updates may still leak sensitive information. Secure aggregation protocols are considered an effective solution for privacy protection in Federated Learning. However, in large-scale federated learning systems, designing efficient and practical secure aggregation remains a critical challenge. Moreover, while secure aggregation effectively conceals model updates, it unintentionally...

Multi-input functional encryption is a primitive that allows for the evaluation of an $\ell$-ary function over multiple ciphertexts, without learning any information about the underlying plaintexts. This type of computation is useful in many cases where one has to compute over encrypted data, such as privacy-preserving cloud services, federated learning, or more generally delegation of computation from multiple clients. It has recently been shown by Alborch et al. in PETS '24 to be useful to...

\textit{Federated Learning} (FL) is a distributed machine learning paradigm that allows multiple clients to train models collaboratively without sharing local data. Numerous works have explored security and privacy protection in FL, as well as its integration with blockchain technology. However, existing FL works still face critical issues. \romannumeral1) It is difficult to achieving \textit{poisoning robustness} and \textit{data privacy} while ensuring high \textit{model accuracy}....

Distributed mean estimation (DME) is a fundamental and important task as it serves as a subroutine in convex optimization, aggregate statistics, and, more generally, federated learning. The inputs for distributed mean estimation (DME) are provided by clients (such as mobile devices), and these inputs often contain sensitive information. Thus, protecting privacy and mitigating the influence of malicious adversaries are critical concerns in DME. A surge of recent works has focused on building...

Federated Learning (FL) solutions with central Differential Privacy (DP) have seen large improvements in their utility in recent years arising from the $\textit{matrix mechanism}$, while FL solutions with distributed (more private) DP have lagged behind. In this work, we introduce the $\textit{distributed}$ matrix mechanism to achieve the best-of-both-worlds; better privacy of distributed DP and better utility from the matrix mechanism. We accomplish this using a novel cryptographic protocol...

Recent advances in differentially private federated learning (DPFL) algorithms have found that using correlated noise across the rounds of federated learning (DP-FTRL) yields provably and empirically better accuracy than using independent noise (DP-SGD). While DP-SGD is well-suited to federated learning with a single untrusted central server using lightweight secure aggregation protocols, secure aggregation is not conducive to implementing modern DP-FTRL techniques without assuming a trusted...

In August 2021, Liu et al. (IEEE TIFS'21) proposed a privacy-enhanced framework named PEFL to efficiently detect poisoning behaviours in Federated Learning (FL) using homomorphic encryption. In this article, we show that PEFL does not preserve privacy. In particular, we illustrate that PEFL reveals the entire gradient vector of all users in clear to one of the participating entities, thereby violating privacy. Furthermore, we clearly show that an immediate fix for this issue is still...

Federated Learning (FL) enables multiple clients to collaboratively train a machine learning model while keeping their data private, eliminating the need for data sharing. Two common approaches to secure aggregation (SA) in FL are the single-aggregator and multiple-aggregator models. This work focuses on improving the multiple-aggregator model. Existing multiple-aggregator protocols such as Prio (NSDI 2017), Prio+ (SCN 2022), Elsa (S&P 2023) either offer robustness only in the...

Time-Lock Puzzles (TLPs) have been developed to securely transmit sensitive information into the future without relying on a trusted third party. Multi-instance TLP is a scalable variant of TLP that enables a server to efficiently find solutions to different puzzles provided by a client at once. Nevertheless, existing multi-instance TLPs lack support for (verifiable) homomorphic computation. To address this limitation, we introduce the "Multi-Instance partially Homomorphic TLP" (MH-TLP), a...

Private Stream Aggregation (PSA) allows clients to send encryptions of their private values to an aggregator that is then able to learn the sum of these values but nothing else. It has since found many applications in practice, e.g. for smart metering or federated learning. In 2018, Becker et al. proposed the first lattice-based PSA scheme LaPS (NDSS 2018), with putative post-quantum security, which has subsequently been patented. In this paper, we describe two attacks on LaPS that break the...

Deduplication is a vital preprocessing step that enhances machine learning model performance and saves training time and energy. However, enhancing federated learning through deduplication poses challenges, especially regarding scalability and potential privacy violations if deduplication involves sharing all clients’ data. In this paper, we address the problem of deduplication in a federated setup by introducing a pioneering protocol, Efficient Privacy-Preserving Multi-Party Deduplication...

Threshold secret sharing enables distributing a message to $n$ parties such that no subset of fewer than $t$ parties can learn the message, whereas any subset of at least $t$ parties can recover the message. Despite being a fundamental primitive, secret sharing still suffers from one significant drawback, where its message reconstruction algorithm is computationally expensive for large privacy thresholds $t$. In this paper, we aim to address this significant drawback. We study general...

Enhancing privacy in federal learning (FL) without considering robustness can create an open door for attacks such as poisoning attacks on the FL process. Thus, addressing both the privacy and security aspects simultaneously becomes vital. Although, there are a few solutions addressing both privacy and security in the literature in recent years, they have some drawbacks such as requiring two non-colluding servers, heavy cryptographic operations, or peer-to-peer communication topology. In...

To securely transmit sensitive information into the future, Time-Lock Puzzles (TLPs) have been developed. Their applications include scheduled payments, timed commitments, e-voting, and sealed-bid auctions. Homomorphic TLP is a key variant of TLP that enables computation on puzzles from different clients. This allows a solver/server to tackle only a single puzzle encoding the computation's result. However, existing homomorphic TLPs lack support for verifying the correctness of the...

Oblivious Transfer (OT) is a fundamental cryptographic protocol with applications in secure Multi-Party Computation, Federated Learning, and Private Set Intersection. With the advent of quantum computing, it is crucial to develop unconditionally secure core primitives like OT to ensure their continued security in the post-quantum era. Despite over four decades since OT's introduction, the literature has predominantly relied on computational assumptions, except in cases using unconventional...

Collaborative graph learning represents a learning paradigm where multiple parties jointly train a graph neural network (GNN) using their own proprietary graph data. To honor the data privacy of all parties, existing solutions for collaborative graph learning are either based on federated learning (FL) or secure machine learning (SML). Although promising in terms of efficiency and scalability due to their distributed training scheme, FL-based approaches fall short in providing provable...

Secure Aggregation (SA) stands as a crucial component in modern Federated Learning (FL) systems, facilitating collaborative training of a global machine learning model while protecting the privacy of individual clients' local datasets. Many existing SA protocols described in the FL literature operate synchronously, leading to notable runtime slowdowns due to the presence of stragglers (i.e. late-arriving clients). To address this challenge, one common approach is to consider stragglers as...

In a federated learning (FL) system, decentralized data owners (clients) could upload their locally trained models to a central server, to jointly train a global model. Malicious clients may plant backdoors into the global model through uploading poisoned local models, causing misclassification to a target class when encountering attacker-defined triggers. Existing backdoor defenses show inconsistent performance under different system and adversarial settings, especially when the malicious...

Our work aims to minimize interaction in secure computation due to the high cost and challenges associated with communication rounds, particularly in scenarios with many clients. In this work, we revisit the problem of secure aggregation in the single-server setting where a single evaluation server can securely aggregate client-held individual inputs. Our key contribution is the introduction of One-shot Private Aggregation ($\mathsf{OPA}$) where clients speak only once (or even choose not to...

Vertical Federated Learning (VFL) is becoming a standard collaborative learning paradigm with various practical applications. Randomness is essential to enhancing privacy in VFL, but introducing too much external randomness often leads to an intolerable performance loss. Instead, as it was demonstrated for other federated learning settings, leveraging internal randomness —as provided by variational autoencoders (VAEs) —can be beneficial. However, the resulting privacy has never been...

Existing oblivious systems offer robust security by concealing memory access patterns, but they encounter significant scalability and performance challenges. Recent efforts to enhance the practicality of these systems involve embedding oblivious computation, e.g., oblivious sorting and shuffling, within Trusted Execution Environments (TEEs). For instance, oblivious sort has been heavily utilized: in Oblix (S&P'18), when oblivious indexes are created and accessed; in Snoopy's high-throughput...

Nowadays Federated learning (FL) is established as one of the best techniques for collaborative machine learning. It allows a set of clients to train a common model without disclosing their sensitive and private dataset to a coordination server. The latter is in charge of the model aggregation. However, FL faces some problems, regarding the security of updates, integrity of computation and the availability of a server. In this paper, we combine some new ideas like clients’ reputation with...

Federated learning enables collaborative model training while preserving data privacy by keeping data local. To protect user privacy during model aggregation, secure aggregation (SA) protocols are widely adopted to mask models. However, existing SA protocols require at least three round trips per aggregation and lack mechanisms to verify aggregation results. Verifiable SA addresses the verification gap but incurs high communication costs. TEE-based SA minimizes round trips but faces...

Federated Learning (FL) is a data-minimization approach enabling collaborative model training across diverse clients with local data, avoiding direct data exchange. However, state-of-the-art FL solutions to identify fraudulent financial transactions exhibit a subset of the following limitations. They (1) lack a formal security definition and proof, (2) assume prior freezing of suspicious customers’ accounts by financial institutions (limiting the solutions’ adoption), (3) scale poorly,...

Federated Learning (FL) accomplishes collaborative model training without the need to share local training data. However, existing FL aggregation approaches suffer from inefficiency, privacy vulnerabilities, and neglect of poisoning attacks, severely impacting the overall performance and reliability of model training. In order to address these challenges, we propose SuperFL, an efficient two-server aggregation scheme that is both privacy preserving and secure against poisoning attacks. The...

We consider how to design an anonymous data collection protocol that enforces compliance rules. Imagine that each client contributes multiple data items (e.g., votes, location crumbs, or secret shares of its input) to an anonymous network, which mixes all clients' data items so that the receiver cannot determine which data items belong to the same user. Now, each user must prove to an auditor that the set it contributed satisfies a compliance predicate, without identifying which items it...

In the setting of solitary output computations, only a single designated party learns the output of some function applied to the private inputs of all participating parties with the guarantee that nothing beyond the output is revealed. The setting of solitary output functionalities is a special case of secure multiparty computation, which allows a set of mutually distrusting parties to compute some function of their private inputs. The computation should guarantee some security properties,...

We propose a novel protocol, Falkor, for secure aggregation for Federated Learning in the multi-server scenario based on masking of local models via a stream cipher based on AES in counter mode and accelerated by GPUs running on the aggregating servers. The protocol is resilient to client dropout and has reduced clients/servers communication cost by a factor equal to the number of aggregating servers (compared to the naïve baseline method). It scales simultaneously in the two major...

Secure aggregation is commonly used in federated learning (FL) to alleviate privacy concerns related to the central aggregator seeing all parameter updates in the clear. Unfortunately, most existing secure aggregation schemes ignore two critical orthogonal research directions that aim to (i) significantly reduce client-server communication and (ii) mitigate the impact of malicious clients. However, both of these additional properties are essential to facilitate cross-device FL with thousands...

In a vertical federated learning (VFL) system consisting of a central server and many distributed clients, the training data are vertically partitioned such that different features are privately stored on different clients. The problem of split VFL is to train a model split between the server and the clients. This paper aims to address two major challenges in split VFL: 1) performance degradation due to straggling clients during training; and 2) data and model privacy leakage from clients’...

Federated learning (FL) has gained widespread popularity in a variety of industries due to its ability to locally train models on devices while preserving privacy. However, FL systems are susceptible to i) privacy inference attacks and ii) poisoning attacks, which can compromise the system by corrupt actors. Despite a significant amount of work being done to tackle these attacks individually, the combination of these two attacks has received limited attention in the research community. To...

This paper introduces Flamingo, a system for secure aggregation of data across a large set of clients. In secure aggregation, a server sums up the private inputs of clients and obtains the result without learning anything about the individual inputs beyond what is implied by the final sum. Flamingo focuses on the multi-round setting found in federated learning in which many consecutive summations (averages) of model weights are performed to derive a good model. Previous protocols, such as...

Aggregate statistics derived from time-series data collected by individual users are extremely beneficial in diverse fields, such as e-health applications, IoT-based smart metering networks, and federated learning systems. Since user data are privacy-sensitive in many cases, the untrusted aggregator may only infer the aggregation without breaching individual privacy. To this aim, secure aggregation techniques have been extensively researched over the past years. However, most existing...

Federated learning (FL) is an increasingly popular approach for machine learning (ML) in cases where the train- ing dataset is highly distributed. Clients perform local training on their datasets and the updates are then aggregated into the global model. Existing protocols for aggregation are either inefficient, or don’t consider the case of malicious actors in the system. This is a major barrier in making FL an ideal solution for privacy-sensitive ML applications. We present ELSA,...

In this work, we introduce a lightweight communication-efficient multi-key approach suitable for the Federated Averaging rule. By combining secret-key RLWE-based HE, additive secret sharing and PRFs, we reduce approximately by a half the communication cost per party when compared to the usual public-key instantiations, while keeping practical homomorphic aggregation performances. Additionally, for LWE-based instantiations, our approach reduces the communication cost per party from quadratic...

Additively Homomorphic Encryption (AHE) has been widely used in various applications, such as federated learning, blockchain, and online auctions. Elliptic Curve (EC) based AHE has the advantages of efficient encryption, homomorphic addition, scalar multiplication algorithms, and short ciphertext length. However, EC-based AHE schemes require solving a small exponential Elliptic Curve Discrete Logarithm Problem (ECDLP) when running the decryption algorithm, i.e., recovering the plaintext...

We focus on the problem of efficiently deploying a federated learning training task in a decentralized setting with multiple aggregators. To that end, we introduce a number of improvements and modifications to the recently proposed IPLS protocol. In particular, we relax its assumption for direct communication across participants, using instead indirect communication over a decentralized storage system, effectively turning it into a partially asynchronous protocol. Moreover, we secure it...

Modern Singular Value Decomposition (SVD) computation dates back to the 1960s when the basis for the eigensystem package and linear algebra package routines was created. Since then, SVD has gained attraction and been widely applied in various scenarios, such as recommendation systems and principal component analyses. Federated SVD has recently emerged, where different parties could collaboratively compute SVD without exchanging raw data. Besides its inherited privacy protection, noise...

This work addresses the security flaw in the original VeriFL protocol and proposes a patched protocol. The patched protocol is secure against any static malicious adversary with a certain threshold and only introduces moderate modifications to the original protocol.

We consider a federated representation learning framework, where with the assistance of a central server, a group of $N$ distributed clients train collaboratively over their private data, for the representations (or embeddings) of a set of entities (e.g., users in a social network). Under this framework, for the key step of aggregating local embeddings trained at the clients in a private manner, we develop a secure embedding aggregation protocol named SecEA, which provides...

This work introduces MicroSecAgg, a framework that addresses the intricacies of secure aggregation in the single-server landscape, specifically tailored to situations where distributed trust among multiple non-colluding servers presents challenges. Our protocols are purpose-built to handle situations featuring multiple successive aggregation phases among a dynamic pool of clients who can drop out during the aggregation. Our different protocols thrive in three distinct cases: firstly, secure...

We consider a foundational unsupervised learning task of k-means data clustering, in a federated learning (FL) setting consisting of a central server and many distributed clients. We develop SecFC, which is a secure federated clustering algorithm that simultaneously achieves 1) universal performance: no performance loss compared with clustering over central- ized data, regardless of data distribution across clients; 2) data privacy: each client’s private data and the cluster centers are not...

Deep learning (DL) models for natural language processing (NLP) tasks often handle private data, demanding protection against breaches and disclosures. Data protection laws, such as the European Union's General Data Protection Regulation (GDPR), thereby enforce the need for privacy. Although many privacy-preserving NLP methods have been proposed in recent years, no categories to organize them have been introduced yet, making it hard to follow the progress of the literature. To close this...

While the convergence of Artificial Intelligence (AI) techniques with improved information technology systems ensured enormous benefits to the Internet of Vehicles (IoVs) systems, it also introduced an increased amount of security and privacy threats. To ensure the security of IoVs data, privacy preservation methodologies have gained significant attention in the literature. However, these strategies also need specific adjustments and modifications to cope with the advances in IoVs design....

As an emerging joint learning model, federated deep learning is a promising way to combine model parameters of different users for training and inference without collecting users’ original data. However, a practical and efficient solution has not been established in previous work due to the absence of effcient matrix computation and cryptography schemes in the privacy-preserving federated learning model, especially in partially homomorphic cryptosystems. In this paper, we propose a practical...

Federated learning (FL), as an emerging distributed learning framework, can combine training from different users without collecting users’ original data, protecting privacy to a certain extent. However, there are no efficient privacy protection technologies applicable to IoT. One challenge in IoT is to reduce the client-server communication cost and solve communication failure questions. Another challenge is how to utilize highquality data to guarantee training performance. To solve these...

\textit{Privacy} and \textit{Byzantine-robustness} are two major concerns of federated learning (FL), but mitigating both threats simultaneously is highly challenging: privacy-preserving strategies prohibit access to individual model updates to avoid leakage, while Byzantine-robust methods require access for comprehensive mathematical analysis. Besides, most Byzantine-robust methods only work in the \textit{honest-majority} setting. We present $\mathsf{FLOD}$, a novel oblivious defender for...

Secure aggregation is a critical component in federated learning, which enables the server to learn the aggregate model of the users without observing their local models. Conventionally, secure aggregation algorithms focus only on ensuring the privacy of individual users in a single training round. We contend that such designs can lead to significant privacy leakages over multiple training rounds, due to partial user selection/participation at each round of federated learning. In fact, we...

We propose a novel primitive called NIVA that allows the distributed aggregation of multiple users' secret inputs by multiple untrusted servers. The returned aggregation result can be publicly verified in a non-interactive way, i.e. the users are not required to participate in the aggregation except for providing their secret inputs. NIVA allows the secure computation of the sum of a large amount of users' data and can be employed, for example, in the federated learning setting in order to...

Federated learning (FL) is an emerging distributed machine learning paradigm which addresses critical data privacy issues in machine learning by enabling clients, using an aggregation server (aggregator), to jointly train a global model without revealing their training data. Thereby, it improves not only privacy but is also efficient as it uses the computation power and data of potentially millions of clients for training in parallel. However, FL is vulnerable to so-called inference attacks...

Secure multi-party computation (MPC) allows multiple parties to perform secure joint computations on their private inputs. Today, applications for MPC are growing with thousands of parties wishing to build federated machine learning models or trusted setups for blockchains. To address such scenarios we propose a suite of novel MPC protocols that maximize throughput when run with large numbers of parties. In particular, our protocols have both communication and computation complexity that...

Federated learning (FL) allows to train a massive amount of data privately due to its decentralized structure. Stochastic gradient descent (SGD) is commonly used for FL due to its good empirical performance, but sensitive user information can still be inferred from weight updates shared during FL iterations. We consider Gaussian mechanisms to preserve local differential privacy (LDP) of user data in the FL model with SGD. The trade-offs between user privacy, global utility, and transmission...

Federated Learning (FL) is a collaborative machine learning approach allowing participants to jointly train a model without having to share their private, potentially sensitive local datasets with others. Despite its benefits, FL is vulnerable to so-called backdoor attacks, in which an adversary injects manipulated model updates into the federated model aggregation process so that the resulting model will provide targeted false predictions for specific adversary-chosen inputs. Proposed...

Recently, privacy-preserving logistic regression techniques on distributed data among several data owners drew attention in terms of their applicability in federated learning environment. Many of them have been built upon cryptographic primitives such as secure multiparty computations(MPC) and homomorphic encryptions(HE) to protect the privacy of data. The secure multiparty computation provides fast and secure unit operations for arithmetic and bit operations but they often does not scale...

Recently introduced federated learning is an attractive framework for the distributed training of deep learning models with thousands of participants. However, it can potentially be used with malicious intent. For example, adversaries can use their smartphones to jointly train a classifier for extracting secret keys from the smartphones' SIM cards without sharing their side-channel measurements with each other. With federated learning, each participant might be able to create a strong model...

Federated learning is gaining significant interests as it enables model training over a large volume of data that is distributedly stored over many users, while protecting the privacy of the individual users. However, a major bottleneck in scaling federated learning to a large number of users is the overhead of secure model aggregation across many users. In fact, the overhead of state-of-the-art protocols for secure model aggregation grows quadratically with the number of users. We propose a...

Developing machine learning models from federated training data, containing many independent samples, is an important task that can significantly enhance the potential applicability and prediction power of learned models. Since single users, like hospitals or individual labs, typically collect data-sets that do not support accurate learning with high confidence, it is desirable to combine data from several users without compromising data privacy. In this paper, we develop a...

Federated Learning (FL) enables a large number of users to jointly learn a shared machine learning (ML) model, coordinated by a centralized server, where the data is distributed across multiple devices. This approach enables the server or users to train and learn an ML model using gradient descent, while keeping all the training data on users' devices. We consider training an ML model over a mobile network where user dropout is a common phenomenon. Although federated learning was aimed at...

Deep learning can achieve higher accuracy than traditional machine learning algorithms in a variety of machine learning tasks. Recently, privacy-preserving deep learning has drawn tremendous attention from information security community, in which neither training data nor the training model is expected to be exposed. Federated learning is a popular learning mechanism, where multiple parties upload local gradients to a server and the server updates model parameters with the collected...

We design a novel, communication-efficient, failure-robust protocol for secure aggregation of high-dimensional data. Our protocol allows a server to compute the sum of large, user-held data vectors from mobile devices in a secure manner (i.e. without learning each user's individual contribution), and can be used, for example, in a federated learning setting, to aggregate user-provided model updates for a deep neural network. We prove the security of our protocol in the honest-but-curious and...