ML Detection of Quantum-Vulnerable Cryptography in Files
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cryptographic systems are vulnerable to quantum computing technologies, which threaten the security provided by asymmetric cryptography.
Innovation Solution
A machine learning (ML) model is trained to identify and replace vulnerable cryptographic algorithms with quantum-resistant alternatives by recognizing specific features of asymmetric cryptography algorithms, using deep neural networks (DNNs) or support vector machines (SVMs) to detect and mitigate vulnerabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If asymmetric cryptography algorithms are used to provide security, then security is provided, but vulnerability to quantum computing threats increases
Solution Approach 1:
The patent applies preliminary action by proactively identifying cryptographic algorithms that are vulnerable to quantum computing before actual quantum threats materialize. The system scans codebases, documentation, and configuration files to detect asymmetric cryptography implementations (RSA, ECC, Diffie-Hellman) and flags them for replacement with quantum-resistant alternatives, enabling security teams to address vulnerabilities before quantum computers become capable of breaking them.
Solution Approach 2:
The patent applies parameter changes by transitioning from asymmetric cryptographic parameters (public/private key pairs based on mathematical problems solvable by quantum algorithms) to symmetric cryptographic parameters or post-quantum cryptographic parameters that are resistant to quantum attacks. This involves changing the fundamental cryptographic primitives and their mathematical foundations to ensure future-proof security.
2Measurement precision
If manual identification of cryptographic algorithms is performed, then accuracy can be maintained, but time consumption and resource usage increase
Solution Approach 1:
The patent applies mechanics substitution by replacing the manual mechanical process of cryptographic algorithm identification with an automated computer-based system. The system uses pattern recognition, text analysis, and code scanning algorithms to automatically detect asymmetric cryptography implementations across large codebases, documentation, and configuration files, dramatically reducing identification time while maintaining or improving accuracy compared to manual review.
3Reliability
If comprehensive scanning of all files and documentation is performed, then identification completeness is improved, but computational resources and processing time increase
Solution Approach 1:
The patent applies segmentation by dividing the comprehensive scanning task into distinct segments: code file scanning, documentation scanning, and configuration file scanning. Each segment is processed with appropriate techniques and priority levels, allowing the system to achieve high identification completeness across all file types while optimizing resource allocation and processing efficiency for each segment type.
Data Source
AI summary
Systems, devices, methods, and computer-readable media provide automatic detection of cryptographic algorithms susceptible to compromise by a quantum computer. A method includes receiving, by a trained machine learning (ML) model, a file; executing the trained ML model on the file to generate an output, the output indicating, for each cryptography algorithm of a plurality of cryptography algorithms that are susceptible to compromise by a quantum computer, whether the cryptography algorithm is embodied in or used by the file. Responsive to determining at least one of the cryptography algorithms is embodied or used in the file, performing a mitigation action that reduces or eliminates a vulnerability of the file to compromise by a quantum computer.