As federated learning (FL) keeps dominating the way in privacy-preserving machine learning (ML), notably in finance, its long-term sustainability is confronted with the approaching challenge of quantum computing. The introduction of quantum computing poses a challenge to traditional cryptographic technique on which FL relies RSA, elliptic curve cryptography (ECC), and some homomorphic encryption (HE) methods applied for encrypting model updates during training rendering this chapter to explore the interplay between the threat of quantum computing and the FL architectures, with emphasis on the implications this interaction introduces to cybersecurity and privacy in finance applications. Quantum computers are theoretically capable of solving hard math problems that have been regarded as computationally intractable for quantum computers. The well-known algorithms like Shor’s and Grover’s provides serious risk to the cryptographic procedures FL pipelines depends on. The finance sector, by its nature involving sensitive data and dependence on secure, distributed ML systems, is particularly vulnerable. The chapter begins by summarizing the fundamentals of FL and current encryption methods adapted to protect FL workflows. It then shifts towards the essence of quantum computing, emphasizing on the notable algorithms that threaten FL. We also explore potential attack points through which quantum computing could attack FL, e.g., model inversion attacks, poisoning attacks facilitated by quantum capabilities, and threats to secure aggregation. Post-quantum cryptography (PQC) is also presented as a potential counterattack, followed by a discussion of its use case in FL platforms. This chapter attempts to close the gap between FL and quantum computing threats to the financial sector. It is an introduction to practitioners and researchers to revisit examining security assumptions in FL and move towards the quantum-augmented cyber threat model.
As federated learning (FL) keeps dominating the way in privacy-preserving machine learning (ML), notably in finance, its long-term sustainability is confronted with the approaching challenge of quantum computing. The introduction of quantum computing poses a challenge to traditional cryptographic technique on which FL relies RSA, elliptic curve cryptography (ECC), and some homomorphic encryption (HE) methods applied for encrypting model updates during training rendering this chapter to explore the interplay between the threat of quantum computing and the FL architectures, with emphasis on the implications this interaction introduces to cybersecurity and privacy in finance applications. Quantum computers are theoretically capable of solving hard math problems that have been regarded as computationally intractable for quantum computers. The well-known algorithms like Shor’s and Grover’s provides serious risk to the cryptographic procedures FL pipelines depends on. The finance sector, by its nature involving sensitive data and dependence on secure, distributed ML systems, is particularly vulnerable. The chapter begins by summarizing the fundamentals of FL and current encryption methods adapted to protect FL workflows. It then shifts towards the essence of quantum computing, emphasizing on the notable algorithms that threaten FL. We also explore potential attack points through which quantum computing could attack FL, e.g., model inversion attacks, poisoning attacks facilitated by quantum capabilities, and threats to secure aggregation. Post-quantum cryptography (PQC) is also presented as a potential counterattack, followed by a discussion of its use case in FL platforms. This chapter attempts to close the gap between FL and quantum computing threats to the financial sector. It is an introduction to practitioners and researchers to revisit examining security assumptions in FL and move towards the quantum-augmented cyber threat model.
Collaborative threat intelligence via federated learning (FL) faces critical risks from quantum computing, which can compromise classical encryption methods. This study proposes a quantum-secure FL framework using post-quantum cryptography (PQC) to protect cross-organizational data sharing. We expose vulnerabilities in traditional FL through simulated quantum attacks on RSA encrypted gradients and introduce a hybrid architecture integrating NIST-standardized algorithms CRYSTALS-Kyber for key exchange and CRYSTALS-Dilithium for authentication. Testing on APT attack datasets demonstrated 97.6% threat detection accuracy with minimal latency overhead (18.7%), validating real-world viability. A healthcare consortium case study confirmed secure ransomware indicator sharing without breaching privacy regulations. The work highlights the urgency of quantum ready defenses and provides technical guidelines for deploying PQC in FL systems, alongside policy recommendations for standardizing quantum resilience in threat-sharing networks.
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.
As artificial intelligence (AI) systems increasingly underpin critical applications in healthcare, finance, defense, and infrastructure, ensuring their security has become paramount. However, the rapid advancement of quantum computing poses a significant threat to classical cryptographic schemes that currently safeguard these systems. Quantum algorithms such as Shor’s and Grover’s threaten to undermine the confidentiality, integrity, and authentication of data and models that AI systems depend on. In this context, Post-Quantum Cryptography (PQC) has emerged as a crucial area of research aimed at developing cryptographic algorithms that are secure against both classical and quantum adversaries. This paper investigates the intersection of quantum computing threats and AI system vulnerabilities, highlighting how current security mechanisms may fail in a post-quantum era. We explore various categories of PQC—including lattice-based, hash-based, and multivariate polynomial cryptography—and evaluate their applicability to securing AI systems, particularly in scenarios such as model distribution, federated learning, data encryption, and communication in AI-enabled edge and IoT environments. Through analysis of emerging use cases and proposed architectures, the paper outlines how PQC can be integrated into the AI lifecycle to mitigate quantum-era threats. It also identifies key challenges such as computational overhead, integration complexity, and standardization gaps. The study concludes by outlining future research opportunities, including the development of efficient PQC protocols tailored to AI workloads, the creation of quantum-resilient AI pipelines, and the importance of interdisciplinary collaboration to secure AI’s future.
The modern banking sector faces growingcybersecurity challenges, demanding collaborative yet privacypreservingdefense mechanisms. Federated Learning (FL) hasemerged as a key paradigm for addressing these needs, but theadvent of quantum computing threatens its long-term viability.This development introduces a critical duality: the existentialthreat of quantum capabilities to break classical cryptography andthe transformative opportunities offered by Quantum MachineLearning (QML). While research has addressed these aspectsseparately, a unified analysis that unites them is lacking. Thispaper presents the first comprehensive systematic review mappingthis dualistic landscape. Following PRISMA guidelines, the reviewsynthesizes the current state of research and evaluates thechallenges and opportunities at the intersection of FL, quantumcomputing, and financial cybersecurity. The findings reveala strong consensus on the urgent need to integrate Post-QuantumCryptography (PQC) to secure FL frameworks against futurethreats. Simultaneously, a long-term vision is emerging to leverageQML to enhance threat detection capabilities beyond classicalboundaries. A significant trend toward integrated, layeredarchitectures that combine FL, blockchain, and quantumtechnologies is also identified. This review concludes that theevolution of FL in banking is inextricably linked to quantumadvances, demanding a two-pronged proactive strategy: mitigatingimmediate risks with PQC while strategically investing in R&D forQML.
Machine learning models in online environments are vulnerable to various adversarial attacks, such as those from generative adversarial networks (GANs) attacks and more powerful attacks based on recent advances in quantum computing. Federated Learning (FL), a modern privacy preserving distributed machine learning technique, also faces modern data management concerns related to quantum computing. Limiting adversarial learning through quantum mechanics lends itself as an effective security mechanism. This paper introduces a novel quantumencrypted FL framework that integrates randomly-generated quantum noise into an FL environment to improve security against adversarial learning algorithms. These algorithms can conduct reconstruction attacks, which increase privacy leakage through adversarially generated data. Specifically, GAN attacks are effective at creating data samples that resemble training data. Traditional computing techniques can be improved by appending random noise generated by quantum computers as a quantum verification method. The proposed hybrid-quantum encryption approach can fortify a network against generative reconstruction attacks by adding quantum noise to each participant's training data samples. To evaluate the effectiveness of the proposed quantum encryption techniques for protecting FL against GANs, we encrypt the MNIST dataset with quantum-generated keys and then distribute the data in a privacy-preserving manner.
Federated Learning (FL) enables collaborative machine learning by aggregating local models from decentralized clients without sharing raw data. However, the parameter exchange process in standard FL architectures is vulnerable to emerging quantum computing threats. Specifically, Shor's algorithm, executable on large-scale quantum computers, can break conventional asymmetric cryptography such as RSA and ECDH in polynomial time, thereby threatening the security of FL systems that rely on these traditional public-key infrastructures for parameter exchange. This study addresses this vulnerability by implementing the recently standardized post-quantum cryptographic protocol, ML-KEM (Module-Lattice-Based Key-Encapsulation Mechanism), within a FedAvg-based FL architecture. The integration is designed to secure the parameter exchange pipeline without compromising the neural network's performance. Experimental results on a simulated environment utilizing the MNIST dataset demonstrate that the ML-KEM integration preserves 100% of the global model accuracy. Furthermore, the cryptographic latency overhead introduced by encapsulation and decapsulation remains highly efficient, proving its potential as a robust security layer. While current evaluations focus on small-scale deployments, the proposed architecture establishes a foundational post-quantum security framework for future privacy-preserving distributed learning systems.