Distributed ledger-based hybrid quantum machine learning ransomware security
View Patent ↗Disclosed are various approaches for distributed ledger-based hybrid quantum ransomware security. In some examples, ransomware detection can be performed on a file. The ransomware detection can include converting the file into image data comprising an image data format, processing the image data using a convolutional neural network to generate a feature map, and providing the feature map to a variational quantum circuit machine learning engine. An action can be performed based at least in part on an output from the variational quantum circuit machine learning engine.
1 . A system, comprising:
at least one computing device comprising at least one processor and at least one memory; and
machine-readable instructions stored in the at least one memory that, when executed by the at least one processor, cause the at least one computing device to at least:
convert a file into image data based at least in part on reformatting a particular data format of the file to an image data format;
process the image data using a convolutional neural network that generates at least one feature map;
provide the at least one feature map to a variational quantum circuit machine learning engine; and
perform at least one action based at least in part on an output from the variational quantum circuit machine learning engine.
2 . The system of claim 1 , wherein the variational quantum circuit machine learning engine and the convolutional neural network are components of a hybrid quantum ransomware detection application that utilizes a digital computing environment and a quantum computing environment to perform the ransomware detection process.
3 . The system of claim 1 , wherein the file is an executable file comprising a binary data format, and the file is converted based at least in part on reformatting the binary data format to the image data format.
4 . The system of claim 1 , wherein the machine-readable instructions, when executed by the at least one processor, further cause the at least one computing device to at least:
process data from the variational quantum circuit machine learning engine using a neural network that provides at least one probability indicating whether the file includes ransomware.
5 . The system of claim 1 , wherein the machine-readable instructions, when executed by the at least one processor, further cause the at least one computing device to at least:
determine that at least one file characteristic specified in a ransomware security automated contract executed in a distributed ledger environment indicates that the file is to be examined for ransomware.
6 . The system of claim 1 , wherein the ransomware detection process is determined to be performed on a file based at least in part on at least one rule specified in a ransomware security automated contract executed in a distributed ledger environment.
7 . A non-transitory, computer-readable medium comprising machine-readable instructions that, when executed by at least one processor of a computing device, cause the at least one computing device to at least:
convert a file into image data based at least in part on reformatting a particular data format of the file to an image data format;
process the image data using a convolutional neural network that generates at least one feature map;
provide the at least one feature map to a variational quantum circuit machine learning engine; and
perform at least one action based at least in part on an output from the variational quantum circuit machine learning engine.
8 . The non-transitory, computer-readable medium of claim 7 , wherein the variational quantum circuit machine learning engine and the convolutional neural network are components of a hybrid quantum ransomware detection application that utilizes a digital computing environment and a quantum computing environment to perform the ransomware detection process.
9 . The non-transitory, computer-readable medium of claim 7 , wherein the file is an executable file comprising a binary data format, and the file is converted based at least in part on reformatting the binary data format to the image data format.
10 . The non-transitory, computer-readable medium of claim 7 , wherein the machine-readable instructions, when executed by the at least one processor, further cause the at least one computing device to at least:
process data from the variational quantum circuit machine learning engine using a neural network that provides at least one probability indicating whether the file includes ransomware.
11 . The non-transitory, computer-readable medium of claim 7 , wherein the machine-readable instructions, when executed by the at least one processor, further cause the at least one computing device to at least:
determine that at least one file characteristic specified in a ransomware security automated contract executed in a distributed ledger environment indicates that the file is to be examined for ransomware.
12 . The non-transitory, computer-readable medium of claim 7 , wherein the ransomware detection process is determined to be performed on a file based at least in part on at least one rule specified in a ransomware security automated contract executed in a distributed ledger environment.
13 . A method, comprising:
converting a file into image data based at least in part on reformatting a particular data format of the file to an image data format;
processing the image data using a convolutional neural network that generates at least one feature map;
providing the at least one feature map to a variational quantum circuit machine learning engine; and
performing at least one action based at least in part on an output from the variational quantum circuit machine learning engine.
14 . The method of claim 13 , wherein the variational quantum circuit machine learning engine and the convolutional neural network are components of a hybrid quantum ransomware detection application that utilizes a digital computing environment and a quantum computing environment to perform the ransomware detection process.
15 . The method of claim 13 , wherein the file is an executable file comprising a binary data format, and the file is converted based at least in part on reformatting the binary data format to the image data format.
16 . The method of claim 13 , further comprising processing data from the variational quantum circuit machine learning engine using a neural network that provides at least one probability indicating whether the file includes ransomware.
17 . The method of claim 13 , further comprising determining that at least one file characteristic specified in a ransomware security automated contract executed in a distributed ledger environment indicates that the file is to be examined for ransomware.
18 . The method of claim 13 wherein the ransomware detection process is determined to be performed on a file based at least in part on at least one rule specified in a ransomware security automated contract executed in a distributed ledger environment.