Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Conference on Communication and Network Security (ICCNS)

A Post-quantum Secure Aggregation for Federated Learning

Shisong Yang, Yuwen Chen, Shanshan Tu, Zhen Yang

Published Dec 1, 2022• 13 citations
Publisher

Abstract

Federated learning is a privacy-preserving machine learning paradigm consisting of local model training, global model aggregation, and global model distribution. Recent research found that model aggregation can reveal the participants’ privacy. To preserve the participants’ privacy, multi-party computation-based secure aggregation is used in federated learning with mobile device participants. The character of the mobile device requires that secure aggregation can be efficient in computation and robust to the dropout. However, prior works need multi rounds, increase computation cost related to the dropped participants, and fails to resist quantum attacks. To solve these issues, we propose a 3-round post-quantum secure protocol for federated learning. In the proposed protocol, single-masking generated by homomorphic Pseudorandom Generator based on learning with round encrypts single user's model. After all the encrypted models are aggregated fast, additively homomorphic decryption based on Shamir secret share guarantee the robustness and performance induced by the dropped participants. All message exchange is based on a post-quantum secure channel constructed with the first post-quantum cryptography standard, Kyber KEM. In post-quantum security, security analysis demonstrates that the proposed protocol can preserve privacy under the sem-honest adversaries setting, and the experimental results show higher running time efficiency.

DOI
10.1145/3586102.3586120

Related papers

Efficient Post-Quantum Cross-Silo Federated Learning Based on Key Homomorphic Pseudo-Random Function

Xiaoyuan Qin, Rui Xu

Federated Learning (FL) enables collaborative model training across distributed users, while preserving data privacy by only sharing model updates. However, secure aggregation, which is essential to prevent data leakage during this process, often incurs significant communication and computational costs. Moreover, existing schemes rarely consider whether they can resist quantum attacks. To address these challenges, we propose an efficient, post-quantum aggregation protocol based on a Key Homomorphic Pseudo-Random Function (KHPRF). Our non-interactive mask elimination mechanism reduces aggregation to a single round, significantly minimizing the communication overhead. Furthermore, the KHPRF keys are reusable, enabling multiple aggregations with a one-time initialization, thereby enhancing efficiency in cross-silo federated learning. Compared to existing schemes, our approach achieves quantum-resistant aggregation with improved efficiency.

Mathematics•Apr 25, 2025•5 citations

Enabling Role of Post-Quantum Secure Multi-Party Private Intersection Protocol in Federated Learning

Xihan Zhao

With the rapid development of quantum computing technology, traditional encryption methods face severe security threats in multi-party privacy intersection protocols in federated learning. In this paper, we propose a new protocol based on post-quantum cryptography. Firstly, lattice-based homomorphic encryption and zero-knowledge proof technology are used to achieve key generation and parameter initialization against quantum attacks. Secondly, ciphertext data encoding is carried out to support homomorphic operations. Next, a zero-knowledge proof is used to verify the correctness of the ciphertext intersection calculation. Finally, the protocol is embedded into the federated learning workflow, adaptively adjusting the parameters. Experimental results show that the protocol achieves the NIST (National Institute of Standards and Technology) security level 3, and the privacy leakage rate is less than 1.2%, the communication and computational costs are controllable, and the protocol does not bring great influence to the accuracy of the federated learning model. The experimental results verify that the protocol can provide a reliable protection for the privacy of federated learning data in the quantum era.

IEEE International Conference on Automation, Electronics and Electrical Engineering (AUTEEE)•Nov 28, 2025•0 citations

SecAgg++: A Post-Quantum Privacy Perserving Federated Learning Protocol

Alessandro Perez, Giulia Cavicchioni, Silvio Cretti +3 more

Secure aggregation is a fundamental building block for privacy-preserving federated learning, yet most existing masking-based secure aggregation protocols do not provide post-quantum security. In this work, we present SecAgg++, a masking-based post-quantum secure aggregation protocol for the single-server setting. SecAgg++ integrates post-quantum cryptographic primitives while preserving the communication and computational efficiency of classical frameworks such as SecAgg and SecAgg+, and supports client dropout handling through an efficient recovery procedure.

ACM Workshop on Artificial Intelligence and Security (AISec)•Nov 9, 2026•0 citations

Quantum Federated Learning: Bridging Quantum Computing and Distributed AI

Tariq Qayyum, Manzoor Ahmed Khan, Asadullah Tariq +4 more

In recent years, the growing demand for secure, efficient, and scalable machine learning has highlighted significant challenges in traditional Federated Learning (FL) systems. These challenges include computational inefficiencies in handling large-scale, high-dimensional data, privacy concerns, and the limitations of classical hardware in solving complex optimization problems. Additionally, the increasing complexity of data and the need for more robust privacy-preserving methods have pushed the boundaries of classical FL. To address these issues, this paper presents a detailed framework for Quantum Federated Learning (QFL), where quantum computing and FL converge to enable distributed quantum model training with enhanced privacy preservation. The system is modeled using local quantum models on clients and a global aggregation strategy at the server. We develop quantum gradient-based optimization with quantum cross-entropy loss, privacy preservation through encryption, and robustness to quantum noise. A set of theorems is provided to prove the correctness and efficiency of the model, supported by rigorous mathematical formulations. We used IBM Qiskit for the simulation and compared our proposed QFL with classical FL. The results demonstrate that our QFL outperformed classical FL in terms of accuracy, precision, recall, and F1 score.

IEEE/ACM International Conference on Utility and Cloud Computing (UCC)•Dec 16, 2024•6 citations

Experimentally Validated Quantum-Secure Federated Learning over a Multi-user Quantum Network

Zhiping Liu, Xiaoyu Cao, Haowen Liu +6 more

Federated learning enables decentralized, privacy-preserving training but remains vulnerable to privacy leakage in the quantum era. Quantum federated learning (QFL) offers a promising path toward enhanced security and efficiency. However, a practical and experimentally validated QFL protocol utilizing near-term quantum techniques to address data privacy has been lacking. Here, we present QuNetQFL, a QFL protocol implemented on quantum networks, in which local model updates are masked with distributed quantum secret keys, offering information-theoretic security during aggregation. We experimentally validate the protocol on a 4-client quantum network and benchmark its performance using the generated keys on quantum and real-world datasets. Adding a single quantum client substantially improves global accuracy for classifying multipartite entangled and nonstabilizer quantum datasets. For language tasks, we apply QuNetQFL to sentiment analysis by federated fine-tuning of a hybrid classical-quantum language model, achieving comparable and robust performance in simulation and on real quantum hardware. Large-scale simulations further demonstrate scalability to 200 clients for handwritten-digit recognition, with rapid convergence and a 75% reduction in communication cost via model compression. Our work establishes a practical and scalable route to quantum-secure federated learning for the emerging quantum internet.

arXiv:2501.12709•Research•Jan 1, 2026•12 citations

PQ-FL: End-to-End Post-Quantum Secure Federated Learning Architecture

Sujith B

Federated Learning (FL) enables collaborative machine learning without centralizing raw data. However, the impending threat of cryptographically-relevant quantum computers exposes FL's reliance on classical public-key cryptography (e.g., RSA, ECC) to Harvest-Now-Decrypt-Later (HNDL) attacks. We present PQ-FL, the first open federated learning control plane secured end-to-end using the finalized NIST Post-Quantum Cryptography (PQC) standards. Our architecture integrates ML-DSA-87 (FIPS 204) for transport-layer identity authentication (mTLS) and ML-KEM-1024 (FIPS 203) for application-layer model payload encryption. To overcome the lack of comprehensive PQC support in standard Python libraries (BoringSSL), we introduce a novel OQS-stunnel sidecar pattern that proxies edge client traffic. We evaluate the system on a CUDA-accelerated edge cluster training a convolutional neural network. Empirical results confirm successful multi-round aggregation using FedAvg, Krum, and Trimmed-Mean strategies alongside differential privacy, achieving seamless PQC key encapsulation (1568-byte ciphertexts) and verifiable asynchronous global model streaming.

•May 25, 2026•0 citations
Federated learning is a privacy-preserving machine learning paradigm consisting of local model training, global model aggregation, and global model distribution. Recent research found that model aggregation can reveal the participants’ privacy. To preserve the participants’ privacy, multi-party computation-based secure aggregation is used in federated learning with mobile device participants. The character of the mobile device requires that secure aggregation can be efficient in computation and robust to the dropout. However, prior works need multi rounds, increase computation cost related to the dropped participants, and fails to resist quantum attacks. To solve these issues, we propose a 3-round post-quantum secure protocol for federated learning. In the proposed protocol, single-masking generated by homomorphic Pseudorandom Generator based on learning with round encrypts single user's model. After all the encrypted models are aggregated fast, additively homomorphic decryption based on Shamir secret share guarantee the robustness and performance induced by the dropped participants. All message exchange is based on a post-quantum secure channel constructed with the first post-quantum cryptography standard, Kyber KEM. In post-quantum security, security analysis demonstrates that the proposed protocol can preserve privacy under the sem-honest adversaries setting, and the experimental results show higher running time efficiency.
Federated Learning (FL) enables collaborative model training across distributed users, while preserving data privacy by only sharing model updates. However, secure aggregation, which is essential to prevent data leakage during this process, often incurs significant communication and computational costs. Moreover, existing schemes rarely consider whether they can resist quantum attacks. To address these challenges, we propose an efficient, post-quantum aggregation protocol based on a Key Homomorphic Pseudo-Random Function (KHPRF). Our non-interactive mask elimination mechanism reduces aggregation to a single round, significantly minimizing the communication overhead. Furthermore, the KHPRF keys are reusable, enabling multiple aggregations with a one-time initialization, thereby enhancing efficiency in cross-silo federated learning. Compared to existing schemes, our approach achieves quantum-resistant aggregation with improved efficiency.
With the rapid development of quantum computing technology, traditional encryption methods face severe security threats in multi-party privacy intersection protocols in federated learning. In this paper, we propose a new protocol based on post-quantum cryptography. Firstly, lattice-based homomorphic encryption and zero-knowledge proof technology are used to achieve key generation and parameter initialization against quantum attacks. Secondly, ciphertext data encoding is carried out to support homomorphic operations. Next, a zero-knowledge proof is used to verify the correctness of the ciphertext intersection calculation. Finally, the protocol is embedded into the federated learning workflow, adaptively adjusting the parameters. Experimental results show that the protocol achieves the NIST (National Institute of Standards and Technology) security level 3, and the privacy leakage rate is less than 1.2%, the communication and computational costs are controllable, and the protocol does not bring great influence to the accuracy of the federated learning model. The experimental results verify that the protocol can provide a reliable protection for the privacy of federated learning data in the quantum era.
Secure aggregation is a fundamental building block for privacy-preserving federated learning, yet most existing masking-based secure aggregation protocols do not provide post-quantum security. In this work, we present SecAgg++, a masking-based post-quantum secure aggregation protocol for the single-server setting. SecAgg++ integrates post-quantum cryptographic primitives while preserving the communication and computational efficiency of classical frameworks such as SecAgg and SecAgg+, and supports client dropout handling through an efficient recovery procedure.
In recent years, the growing demand for secure, efficient, and scalable machine learning has highlighted significant challenges in traditional Federated Learning (FL) systems. These challenges include computational inefficiencies in handling large-scale, high-dimensional data, privacy concerns, and the limitations of classical hardware in solving complex optimization problems. Additionally, the increasing complexity of data and the need for more robust privacy-preserving methods have pushed the boundaries of classical FL. To address these issues, this paper presents a detailed framework for Quantum Federated Learning (QFL), where quantum computing and FL converge to enable distributed quantum model training with enhanced privacy preservation. The system is modeled using local quantum models on clients and a global aggregation strategy at the server. We develop quantum gradient-based optimization with quantum cross-entropy loss, privacy preservation through encryption, and robustness to quantum noise. A set of theorems is provided to prove the correctness and efficiency of the model, supported by rigorous mathematical formulations. We used IBM Qiskit for the simulation and compared our proposed QFL with classical FL. The results demonstrate that our QFL outperformed classical FL in terms of accuracy, precision, recall, and F1 score.
Federated learning enables decentralized, privacy-preserving training but remains vulnerable to privacy leakage in the quantum era. Quantum federated learning (QFL) offers a promising path toward enhanced security and efficiency. However, a practical and experimentally validated QFL protocol utilizing near-term quantum techniques to address data privacy has been lacking. Here, we present QuNetQFL, a QFL protocol implemented on quantum networks, in which local model updates are masked with distributed quantum secret keys, offering information-theoretic security during aggregation. We experimentally validate the protocol on a 4-client quantum network and benchmark its performance using the generated keys on quantum and real-world datasets. Adding a single quantum client substantially improves global accuracy for classifying multipartite entangled and nonstabilizer quantum datasets. For language tasks, we apply QuNetQFL to sentiment analysis by federated fine-tuning of a hybrid classical-quantum language model, achieving comparable and robust performance in simulation and on real quantum hardware. Large-scale simulations further demonstrate scalability to 200 clients for handwritten-digit recognition, with rapid convergence and a 75% reduction in communication cost via model compression. Our work establishes a practical and scalable route to quantum-secure federated learning for the emerging quantum internet.
Federated Learning (FL) enables collaborative machine learning without centralizing raw data. However, the impending threat of cryptographically-relevant quantum computers exposes FL's reliance on classical public-key cryptography (e.g., RSA, ECC) to Harvest-Now-Decrypt-Later (HNDL) attacks. We present PQ-FL, the first open federated learning control plane secured end-to-end using the finalized NIST Post-Quantum Cryptography (PQC) standards. Our architecture integrates ML-DSA-87 (FIPS 204) for transport-layer identity authentication (mTLS) and ML-KEM-1024 (FIPS 203) for application-layer model payload encryption. To overcome the lack of comprehensive PQC support in standard Python libraries (BoringSSL), we introduce a novel OQS-stunnel sidecar pattern that proxies edge client traffic. We evaluate the system on a CUDA-accelerated edge cluster training a convolutional neural network. Empirical results confirm successful multi-round aggregation using FedAvg, Krum, and Trimmed-Mean strategies alongside differential privacy, achieving seamless PQC key encapsulation (1568-byte ciphertexts) and verifiable asynchronous global model streaming.