Blockchain Transaction Validation With Guardian Override
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Blockchain networks are vulnerable to cyberattacks and fraud, leading to significant asset theft, as existing security measures fail to effectively detect and prevent malicious transactions.
Innovation Solution
Implementing a classifier trained with anomaly detection mechanisms, such as pattern recognition and machine learning, to identify suspicious transactions, and incorporating guardian parties or one-time use keys to override false positives, ensuring transaction validation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a classifier trained with anomaly detection is implemented to detect suspicious transactions, then the detection accuracy of fraudulent activities is improved, but the system complexity increases
Solution Approach 1:
A guardian party is introduced as an intermediary between the classifier and the transaction validation process. When the classifier flags a transaction as suspicious, the guardian party reviews the anomaly score and makes the final decision on whether to block or allow the transaction. This mediator resolves the complexity by providing a human-in-the-loop verification mechanism that complements the automated classification system.
Solution Approach 2:
The security system is segmented into multiple independent components: the classifier module that performs initial anomaly detection, the guardian party module that provides oversight for suspicious transactions, and the transaction validation module that executes final decisions. This segmentation allows each component to specialize in specific functions, improving overall detection accuracy while managing system complexity through modular design.
2Reliability
If anomaly detection mechanisms are used to identify suspicious transactions, then the security against cyberattacks is improved, but the false positive rate increases
Solution Approach 1:
The system implements feedback loops where guardian parties review false positive cases and provide corrections to the classifier. The guardian's decisions on suspicious transactions feed back into the system, allowing the classifier to learn from human expertise and gradually reduce false positives while maintaining high security detection capabilities.
Solution Approach 2:
The system dynamically adjusts its operation mode based on the anomaly score. Transactions with low anomaly scores are automatically validated, while those with high scores are routed to guardian review. This dynamic approach allows the system to maintain high security for suspicious transactions while efficiently processing legitimate transactions, thereby reducing false positives.
3Measurement precision
If guardian parties are introduced to override false positives, then the transaction validation accuracy is improved, but the processing time increases
Solution Approach 1:
The guardian party does not review all transactions, but only those that exceed a certain anomaly threshold. This partial action approach allows the system to maintain high validation accuracy for suspicious transactions while avoiding the time cost of human review for every transaction, thus balancing accuracy with processing speed.
Solution Approach 2:
Different levels of review are applied to different transactions based on their anomaly characteristics. High-risk transactions receive full guardian review, while lower-risk transactions undergo automated validation only. This localized quality approach ensures high accuracy where needed while minimizing processing time for routine transactions.
Data Source
AI summary
Systems, methods, and computer programming products leveraging the use of machine learning, cryptographic keys and blockchain technology for validating blockchain transactions. The disclosed systems, methods and products improve detection of malicious cyberattacks and fraud, while reducing occurrences of falsely invalidated transactions and improving overall blockchain security in both permissioned and permissionless blockchain networks. Classifiers are trained using machine learning and other classification techniques by building a transaction history to learn how to identify suspicious transactions on the blockchain. In permissionless and order-execute models of permissioned blockchains, cryptographic keys are publicly registered to guardians residing out of band, who may co-sign requests and override or resubmit transactions marked as suspicious by the classifiers. In an execute-order model of permissioned blockchains, one-time use keys may be registered with the certificate authority of the blockchain, and used to co-sign transactions that might appear suspicious, preventing false-positive identification of suspicious-looking transactions by the classifier.