Temporal Graph Embedding for Blockchain Reordering Attack Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated systems for network intrusion detection, particularly in permissioned blockchain networks like Hyperledger™ Fabric, are inefficient and lack effective methods to detect reordering attacks that compromise secure transactions.
Innovation Solution
A method and apparatus using temporal graphs with latency and ordinal values to encode network messaging, processed by machine learning systems for intrusion detection, generating embeddings that facilitate the detection of reordering attacks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional intrusion detection methods are used in permissioned blockchain networks, then the system structure is simple, but the detection precision is insufficient to identify reordering attacks
Solution Approach 1:
The patent segments the intrusion detection process into distinct functional modules: temporal graph construction module that models message passing events, embedding generation module that converts graphs to vectors, and machine learning classification module that detects reordering attacks. This segmentation enables precise detection while managing system complexity through modular design.
Solution Approach 2:
The patent transforms the intrusion detection problem from traditional feature-based analysis to temporal graph space, where message passing events are represented as vertices and edges with temporal relationships. This dimensional transformation enables the system to capture complex attack patterns that traditional methods miss, improving detection precision.
2Reliability
If real-time detection of reordering attacks is implemented, then the security reliability is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary actions by continuously constructing temporal graphs and generating embeddings from message passing events as they occur in the blockchain network. This ongoing preprocessing ensures that when reordering attacks occur, the system can quickly classify them using the pre-trained machine learning model, reducing detection latency while maintaining high security reliability.
3Difficulty of detecting and measuring
If comprehensive monitoring of message timing and latency is performed, then the detection capability is improved, but the data processing load increases
Solution Approach 1:
The patent extracts only the essential temporal features from comprehensive message monitoring data, specifically focusing on message timing information and latency values that are critical for detecting reordering attacks. By extracting only these key features to construct temporal graphs, the system improves detection capability while avoiding the computational burden of processing all available network data.
Data Source
AI summary
A method and apparatus for detecting network intrusions such as reordering attacks, e.g. in a Hyperledger™ Fabric. A temporal graph is generated which represents actions of nodes according to an ordered secure transaction process, along with latencies and ordinal values of the actions. An embedding of the temporal graph is generated in which the latencies and ordinal values are processed together. The embedding is passed to a detection module such as a machine learning system. Various potential characteristics of, and computations for generating, the embedding are also described.