Industrial innovations, driven by technologies such as the Internet of Things (IoT), cloud computing, and Artificial Intelligence (AI), have revolutionized various operational domains, including supply chain management, equipment monitoring, predictive maintenance, and quality control. Deep Learning (DL) has become instrumental in addressing complex, data-driven challenges within industrial settings, relying on large datasets collected from heterogeneous sources. However, centralizing these datasets on cloud platforms poses significant privacy and security risks. Federated Learning (FL) offers a promising solution by enabling distributed model training across multiple nodes while preventing the exchange of raw data. Despite its advantages, FL introduces new vulnerabilities, especially related to the security of communication channels between participating entities. Traditional cryptographic mechanisms, such as digital signatures and model encryption, can mitigate these risks, but the emergence of quantum computing threatens the robustness of conventional solutions. This work explores the integration of Post-Quantum Cryptography (PQC) into FL to enhance security without incurring significant performance degradation. A modular FL architecture with three security levels is proposed: (i) an unprotected baseline; (ii) authenticated communication using ML-DSA digital signatures; and (iii) full protection combining ML-DSA and ML-KEM-512-based key encapsulation. Implemented within the Flower framework, the architecture is evaluated under simulated MitM attacks. Experimental results demonstrate that PQC-enhanced schemes effectively mitigate quantum-resistant threats while maintaining acceptable computational overhead, thereby ensuring model integrity and data confidentiality.
Industrial innovations, driven by technologies such as the Internet of Things (IoT), cloud computing, and Artificial Intelligence (AI), have revolutionized various operational domains, including supply chain management, equipment monitoring, predictive maintenance, and quality control. Deep Learning (DL) has become instrumental in addressing complex, data-driven challenges within industrial settings, relying on large datasets collected from heterogeneous sources. However, centralizing these datasets on cloud platforms poses significant privacy and security risks. Federated Learning (FL) offers a promising solution by enabling distributed model training across multiple nodes while preventing the exchange of raw data. Despite its advantages, FL introduces new vulnerabilities, especially related to the security of communication channels between participating entities. Traditional cryptographic mechanisms, such as digital signatures and model encryption, can mitigate these risks, but the emergence of quantum computing threatens the robustness of conventional solutions. This work explores the integration of Post-Quantum Cryptography (PQC) into FL to enhance security without incurring significant performance degradation. A modular FL architecture with three security levels is proposed: (i) an unprotected baseline; (ii) authenticated communication using ML-DSA digital signatures; and (iii) full protection combining ML-DSA and ML-KEM-512-based key encapsulation. Implemented within the Flower framework, the architecture is evaluated under simulated MitM attacks. Experimental results demonstrate that PQC-enhanced schemes effectively mitigate quantum-resistant threats while maintaining acceptable computational overhead, thereby ensuring model integrity and data confidentiality.
The rapid growth of the Internet of Things (IoT) is transforming industries such as healthcare, transportation, and smart infrastructure, but it also amplifies critical concerns regarding data security, privacy, and device authentication. Traditional cryptographic mechanisms offer partial protection, yet they remain vulnerable to emerging quantum computing threats, posing significant risks to IoT systems. Addressing these challenges, this paper introduces FLQC-IoT, a novel security framework that integrates federated learning (FL) with quantum computing (QC) to provide robust, scalable, and future-ready protection. Unlike conventional centralized approaches, FLQC-IoT enables decentralized model training directly on IoT devices, safeguarding sensitive data from exposure. Quantum technologies are incorporated at multiple layers: quantum neural networks accelerate optimization tasks, while quantum key distribution and quantum homomorphic encryption ensure tamper-proof key exchange and secure communication. Furthermore, the framework adapts dynamically to emerging threats through real-time anomaly detection and distributed intelligence, significantly enhancing resilience. Experimental results demonstrate a 15.32 % reduction in computational overhead and a 21.45 % decrease in authentication rounds compared to state-of-the-art methods, highlighting the framework’s efficiency and practical readiness. These findings underscore the significance and transformative impact of FLQC-IoT, providing a scalable, privacy-preserving, and resilient approach to securing IoT networks across critical domains, including healthcare, university campus networks, smart infrastructure, and transportation.
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.
Federated learning (FL) provides a collaborative model allowing multiple entities to collectively train artificial intelligence (AI) systems while minimizing data sharing to enhance privacy. Despite its advancements, traditional FL still faces security issues during the exchange of model parameters. The advent of quantum networks, which offer inherent security benefits, prompts us to introduce a new paradigm: quantum communication-based FL (QC-FL). This robust, scalable framework improves data control and mitigates security risks associated with parameter exchange. Our study outlines the key technologies and architecture underpinning QC-FL, illustrating its utility in safeguarding sensitive patient data and enhancing intelligent transportation systems.
The convergence of quantum computing and the scale of Internet of Things (IoT) deployments creates a compounded security problem: classical public-key cryptography securing today’s IoT traffic is vulnerable to harvest-now, decrypt-later attacks, while the constrained hardware typical of IoT devices limits the security mechanisms can be deployed. Prior work has largely evaluated post-quantum cryptography (PQC), federated learning (FL)-based anomaly detection, and quantum-resilient storage separately or in partial combinations, leaving open whether these mechanisms remain practical when composed on constrained hardware under a shared operational budget. This paper answers that question with a three-layer architecture — a hybrid PQC pipeline (Kyber-based key encapsulation, ML-DSA signatures, AES-GCM encryption, and PQC-TLS transport), a federated anomaly-detection layer, and a quantum-resilient storage and audit layer (DeSSE and MuReQua) — executed end-to-end on a Raspberry Pi 5 edge node under AWS IoT Greengrass Core, with nine concurrent virtual IoT nodes processing real attack traffic from the N-BaIoT and TON_IoT datasets. Benchmarking across 27 cryptographic algorithm combinations (810 pipeline executions) shows that all 27 configurations completed in under 2.1 ms, with the deployed Kyber768/ML-DSA-65/AES-256-GCM tier adding 4,521 bytes of per-message overhead, which remained compatible with the evaluated 20 ms inter-row transmission budget. Live federated deployment across the nine virtual IoT nodes on N-BaIoT achieves F1-scores above 0.998 on eight of nine devices, processing at approximately 900 rows/second with zero signature verification failures; a centralized baseline evaluation further confirms 99.46% attack recall on unseen TON_IoT threats withheld from training. The quantum-resilient storage layer maintains 100% chain integrity and complete signature coverage across 4,471 audit records, with independent tamper simulations reliably detected. PQC-TLS introduces a one-time handshake overhead of 13.7 ms (288.5% relative increase) over classical TLS, which remains small relative to the multi-minute FL round intervals measured in the evaluated deployment. Together, these results demonstrate that quantum-resilient cryptography, federated intelligence, and auditable storage can be jointly executed on constrained IoT edge hardware as a single experimentally demonstrated pipeline within the operational conditions evaluated in this study.
Federated learning (FL) has become one of the standard approaches for deploying machine learning models on edge devices, where private training data are distributed across clients, and a shared model is learned by aggregating locally computed updates from each client. While this paradigm enhances communication efficiency by only requiring updates at the end of each training epoch, the transmitted model updates remain vulnerable to malicious tampering, posing risks to the integrity of the global model. Although current digital signature algorithms can protect these communicated model updates, they fail to ensure quantum security in the era of large-scale quantum computing. Fortunately, various post-quantum cryptography algorithms have been developed to address this vulnerability, especially the three NIST-standardized algorithms - Dilithium, FALCON, and SPHINCS+.In this work, we empirically investigate the impact of these three NIST-standardized PQC algorithms for digital signatures within the FL procedure, covering a wide range of models, tasks, and FL settings. Our results indicate that Dilithium stands out as the most efficient PQC algorithm for digital signature in federated learning. Additionally, we offer an in-depth discussion of the implications of our findings and potential directions for future research.
The rapid expansion of Internet of Things (IoT) ecosystems has increased the need for communication mechanisms that can remain secure against emerging computational threats. Conventional asymmetric cryptographic schemes, including RSA and Elliptic Curve Cryptography (ECC), are vulnerable to advances in quantum computing due to the ability of Shor's algorithm to undermine their underlying mathematical assumptions. To address these challenges, this paper presents PQ-IoT SecureCom, a quantum-resistant communication framework built using NIST-standardized post-quantum cryptographic primitives. The proposed framework employs ML-KEM (derived from Kyber) for secure key encapsulation and ML-DSA (derived from Dilithium) for digital authentication, combined with AESGCM to ensure data confidentiality and integrity. Additional security mechanisms, including PQC-based device certification, periodic session key updates, and nonce-based timestamp validation, are incorporated to mitigate replay and impersonation attacks. The framework also supports a hybrid operational mode that enables performance comparison between classical and postquantum cryptographic schemes. System behavior is monitored using a real-time dashboard that records cryptographic overhead, communication metrics, and detected security events. Experimental evaluation shows that ML-KEM and ML-DSA significantly enhance security while introducing computational overhead that remains acceptable for contemporary IoT devices. Through automated attack simulations and detailed event logging, PQ-IoT SecureCom demonstrates the practical feasibility of deploying scalable post-quantum security in IoT communication systems.