Semantic communication (SemCom) has recently gained attention for its ability to achieve high transmission efficiency with minimal data distortion under limited communication resources. However, the strong correlation between source data and channel input leaves SemCom schemes vulnerable to eavesdropping. Additionally, advances in quantum computing threaten traditional cryptographic methods such as RSA due to Shor’s algorithm. To address these risks, a secure SemCom framework with post-quantum protection is essential. This paper presents a post-quantum secure semantic communication (PQSC) framework by integrating learning with errors (LWE) encryption (widely regarded as quantum-resistant) into a VQ-VAE-based SemCom system. The proposed PQSC framework not only resists quantum attacks but also defends against chosen-plaintext attacks. Experiments show that PQSC consistently outperforms baseline methods across various datasets, channel conditions, and SNR levels. To simulate practical wireless environments, we implement channel coding and modulation using Nvidia Sionna, a GPU-accelerated library for physical layer research. We further examine the trade-off between compression efficiency and computational cost. A downlink use case is modeled to analyze recovery quality, energy consumption, and latency. Our mathematical analysis offers insights into system design and parameter selection for real-world deployment.
Semantic communication (SemCom) has recently gained attention for its ability to achieve high transmission efficiency with minimal data distortion under limited communication resources. However, the strong correlation between source data and channel input leaves SemCom schemes vulnerable to eavesdropping. Additionally, advances in quantum computing threaten traditional cryptographic methods such as RSA due to Shor’s algorithm. To address these risks, a secure SemCom framework with post-quantum protection is essential. This paper presents a post-quantum secure semantic communication (PQSC) framework by integrating learning with errors (LWE) encryption (widely regarded as quantum-resistant) into a VQ-VAE-based SemCom system. The proposed PQSC framework not only resists quantum attacks but also defends against chosen-plaintext attacks. Experiments show that PQSC consistently outperforms baseline methods across various datasets, channel conditions, and SNR levels. To simulate practical wireless environments, we implement channel coding and modulation using Nvidia Sionna, a GPU-accelerated library for physical layer research. We further examine the trade-off between compression efficiency and computational cost. A downlink use case is modeled to analyze recovery quality, energy consumption, and latency. Our mathematical analysis offers insights into system design and parameter selection for real-world deployment.
Semantic communication (SemCom) has recently emerged as a promising approach to enhance communication efficiency by transmitting only important semantic information. In eavesdropping environments, the semantic information may be overheard by the eavesdropper even under poor channel conditions with a powerful semantic decoder. Some advanced secure communication deployments such as autoencoder-enhanced Sem-Com (AE-SemCom) and generative model-enhanced SemCom (GEN-SemCom) have been introduced to efficiently transmit the semantic information. However, these secure solutions require retraining the semantic encoder and decoder, which limits the flexibility and practical deployment. To address this issue, we propose a secure SemCom framework for AE-SemCom and GEN-SemCom without altering the parameters of the semantic encoder and decoder. Specifically, we propose to deploy a cooperative jammer to transmit optimized jamming signal to deteriorate the decoding ability of eavesdropper, while a residual refinement module (RRM) is used at the legitimate receiver to mitigate the impact of these jamming signal. Moreover, to achieve an efficient trade-off between transmission security and reliability, we then introduce a cooperative training strategy by formulating this optimization problem as a two-player game between the jammer and Bob. Finally, we conduct extensive simulations to evaluate the effectiveness of the proposed framework across face recognition dataset. In particular, with a jamming power of 0.3, the eavesdropper experiences up to a 12dB reduction in the peak signal-to-noise ratio (PSNR) of reconstructed images compared to the baselines without the proposed security framework while maintaining high-quality image reconstruction for legitimate users.
The rapid development of quantum computing presents a substantial threat to traditional cryptographic algorithms, particularly those relying on mathematical problems such as integer factorization and elliptic curve operations. As a response, the cryptographic community has accelerated the design of post-quantum cryptographic schemes that can withstand attacks from both classical and quantum computers. However, many of these new schemes exhibit inherent trade-offs between performance, key sizes, and implementation complexity. To address this, we propose a novel hybrid cryptographic framework tailored for secure and efficient data transmission in future quantum-aware environments. The proposed system combines three algorithmic paradigms: a lattice-based encryption method for fast and lightweight data protection, a hash-based signature mechanism for authenticity, and a code-based key exchange method to ensure session confidentiality. This layered integration is designed to capitalize on each algorithm’s strengths while mitigating individual limitations. The system is implemented using modular components in a testbed simulating real-world deployments, and its performance is benchmarked across multiple metrics including encryption latency, signature generation time, key sizes, and throughput. Comparative results indicate that the hybrid approach outperforms monolithic schemes in critical areas such as execution time and cryptographic strength under quantum adversary models. The findings support the practicality of using multiple post-quantum primitives in tandem to build robust communication systems. This research contributes a realistic implementation and evaluation of post-quantum security models and highlights key directions for future research and standardization efforts as the global transition to quantum-safe infrastructure begins.
The many forms of wireless communication used these days have created a greater demand for strong and flexible cryptographic methods to protect from new security risks that can happen as quantum computing advances.Diffie-Hellman and RSA approaches have been basic to cryptography, but work on these can now be weakened by attack methods such as Shor's and Grover's algorithms following quantum developments which undermines many post-quantum schemes.In our research, we develop a plan using Quantum Machine Learning (QML) to help ensure the security of future wireless networks.As a result, this design pairs quantum theory with reinforcement learning to create strong keys that cannot be accessed by attackers.Value is drawn from quantum entanglement and random measurements of qubits to create key materials needed for physically unclonable keys and at the same time, reinforcement agents support optimizing agreement policies based on variations detected in the channel.Simulations were run using Rayleigh fading and multi-SNR using Qiskit and TensorFlow.The system achieved entropy greater than 95%, agreed on important issues more than 98% successfully and brought latency down to just 0.13 seconds, outshining both classical and post-quantum cryptography in performance, flexibility and safety from attacks.Moreover, the presented encryption solution managed to resist hackers, even if the environment was noisy.As a quantum-AI combination, it is well-positioned to serve as a platform to safely communicate over wireless networks.It builds the basis for examining embedded QML hardware versions of IoT, vehicle networks and smart grid communications, since fast security and reliable performance without high delay are required.
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.
With the fast-paced development of quantum computing, classical cryptographic techniques are under severe security threats, prompting the need for post-quantum cryptographic mechanisms for secure data exchange in next-generation network communications. Post-quantum cryptography seeks to protect sensitive data against quantum attacks to provide long-term data confidentiality. But all current cryptographic techniques, including RSA and ECC, are susceptible to quantum algorithms like Shor's algorithm, which can factor large integers efficiently and break discrete logarithm problems, making classical cryptography useless. There is thus a pressing need for quantum attack-resistant encryption mechanisms. To meet these challenges, we introduce the Lattice-Based Cryptography with Hybrid Key Exchange (L-CHKE) framework, which combines lattice-based encryption with a hybrid key exchange mechanism. Lattice-based cryptography provides quantum resistance because it is based on hard mathematical problems such as Learning with Errors (LWE), which provides greater security and efficiency. The designed L-CHKE algorithm strengthens secure key distribution and authentication for next-generation networks, especially for applications needing strong security like financial transactions, IoT, and military communications. Experimental results verify that L-CHKE noticeably boosts computational efficiency by 98.45%, decreases key exchange latency by 42.56%, and guarantees robustness by 97.64% against quantum attacks, indicating it is an appropriate solution for post-quantum secure communication.
It is also worth noting that the implementation of quantum computing has been a big threat to the classical cryptographic algorithms that are popular in secure networked systems. PostQuantum Cryptography (PQC) has come to play as one of the viable answers to this issue because it has the capacity to resist quantum-enabled attacks. In this paper, the author offers a detailed performance analysis of post-quantum cryptographic algorithms, lattice-based encryption which is based on the Learning with Errors (LWE) principle, and hashbased digital signatures which is based on SPHINCS+. An experimental environment was created that is controlled by using specific performance measures, such as time of key generation, the latency of encryption and decryption, amount of memory, and the size of keys and ciphertext. To determine the suitability of PQC in guaranteeing confidentiality, integrity, and authenticity over insecure channels, secure network communication was emulated. Through experimental findings, it has been shown that the lattice-based generation of keys has greater overhead in terms of computation and memory, but the encryption, decryption and signature processes have feasible limits. The results validate the practicability of the post-quantum cryptography mechanisms implementation in the practical secure network systems and the trade-off between the increased quantum resistance and the resource consumption.