Post-Quantum Cryptography Optimization via Neural Network Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cryptographic systems, such as RSA and Diffie-Hellman, are vulnerable to quantum computers, which can potentially break modern public-key encryption using algorithms like Shor's and Grover's, posing a threat to data security even before quantum computing capabilities are fully realized, due to the complexity and volume of data that needs to be migrated to quantum-resistant algorithms.
Innovation Solution
A post-quantum cryptography (PQC) system that uses optimization machine learning models to select and implement quantum-resistant cryptographic techniques, such as hash-based, lattice-based, isogeny-based, code-based, and multivariate-based methods, to encrypt and decrypt data, ensuring adaptability and security against quantum attacks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If classical cryptographic algorithms (RSA, Diffie-Hellman) are used, then current computing systems can efficiently process and transmit data, but the system becomes vulnerable to quantum computer attacks that can break these encryption schemes
Solution Approach 1:
The patent transitions from classical cryptographic parameters (based on integer factorization and discrete logarithms) to post-quantum cryptographic parameters (based on lattice problems, code-based problems, or hash-based constructions). This parameter change fundamentally alters the mathematical foundation of the encryption scheme to resist quantum attacks while maintaining operational functionality.
Solution Approach 2:
The patent replaces the mathematical mechanisms underlying classical cryptography (RSA, Diffie-Hellman) with alternative mathematical mechanisms that are quantum-resistant. This substitution involves using entirely different mathematical problems (e.g., lattice-based problems, isogeny-based problems) that cannot be efficiently solved by quantum computers, thereby eliminating the vulnerability to quantum attacks.
2Reliability
If post-quantum cryptographic algorithms are implemented, then quantum-resistant security is achieved, but the complexity and volume of data migration from classical to quantum-resistant systems increases
Solution Approach 1:
The patent performs preliminary actions by pre-generating and storing migration maps that document the relationships between classical cryptographic systems and their post-quantum equivalents. This preliminary documentation includes mapping cryptographic parameters, key relationships, and protocol structures, which simplifies the actual migration process when quantum threats become more pressing.
Solution Approach 2:
The patent introduces migration maps as an intermediary structure that facilitates the transition from classical to post-quantum cryptography. These maps serve as a bridge, providing a structured framework that guides the transformation of cryptographic systems, thereby reducing the complexity of direct migration between the two cryptographic paradigms.
3Reliability
If data is encrypted using multiple PQC techniques, then security against quantum attacks is enhanced, but the transmission time and computational overhead increase
Solution Approach 1:
The patent applies local quality by selecting specific post-quantum cryptographic techniques for specific data types, sensitivity levels, or transmission contexts rather than uniformly applying all PQC techniques to all data. This localized approach allows the system to optimize security for critical data while maintaining faster transmission for less sensitive information, thereby balancing security enhancement with transmission efficiency.
Data Source
AI summary
Systems, apparatuses, methods, and computer program products are disclosed for gathering performance information for post-quantum cryptography (PQC) is provided. An example method includes generating, by a quantum computing (QC) detection data generation circuitry, QC detection data and encrypting, by a PQC cryptographic circuitry and by a first neural network, the QC detection data based on a PQC technique, where the first neural network is trained to encrypt the QC detection data using the PQC technique. The example method further includes decrypting, by a PQC decryption circuitry and by a second neural network, the encrypted QC detection data wherein the second neural network is trained to decrypt data, and storing encryption metadata and decryption metadata as PQC cryptographic performance information associated with the PQC technique.