# US 2026/0093807 A1 · Ransomware attack detection method and related device

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0093807 A1
- Document ID: US20260093807A1
- Status: Published application
- Kind: A1
- Application number: 19/413,487
- Filed: 2025-12-09
- Published: 2026-04-02
- Earliest claimed: 2023-06-13
- Assignees: Huawei Technologies Co., Ltd.
- Applicants: Huawei Technologies Co., Ltd.
- Inventors: Letian Chu; Mengyu Huang; Qizhang Zhou; Gang Hu
- Web page: https://patentgrep.com/patent/US20260093807A1

## CPC

- G06F 21/554: {involving event detection and direct action}
- G06F 21/561: {Virus type analysis}
- G06F 21/55: Detecting local intrusion or implementing counter-measures
- G06F 21/56: Computer malware detection or handling, e.g. anti-virus arrangements
- G06F 21/566: {Dynamic detection, i.e. detection performed at run-time, e.g. emulation, suspicious activities}
- G06F 21/78: to assure secure storage of data (address-based protection against unauthorised use of memory G06F12/14; record carriers for use with machines and with at least a part designed to carry digital markings G06K19/00)
- H04L 63/1416: {Event detection, e.g. attack signature detection}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

An example ransomware attack detection method includes: determining a target fingerprint based on a target input/output (I/O) sequence; determining a similarity between an attack fingerprint in an attack fingerprint library and the target fingerprint based on the attack fingerprint library and the target fingerprint; and determining, based on the similarity between the target fingerprint and the attack fingerprint, that the target I/O sequence is a normal I/O sequence or a ransomware attack I/O sequence.

## Claims

### Claim 1

A ransomware attack detection method, comprising:
determining a target fingerprint based on a target input/output (I/O) sequence, wherein the target I/O sequence is used to access target data;
determining a similarity between an attack fingerprint in an attack fingerprint library and the target fingerprint based on the attack fingerprint library and the target fingerprint, wherein the attack fingerprint library comprises at least one attack fingerprint, and the attack fingerprint is determined based on an attack I/O sequence in a historical ransomware attack; and
determining, based on the similarity, that the target I/O sequence is a normal I/O sequence or a ransomware attack I/O sequence.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the determining the target fingerprint based on the target input/output I/O sequence comprises:
determining the target fingerprint based on a feature of the target I/O sequence, wherein the feature of the target I/O sequence comprises at least one of an instruction comprised in the target I/O sequence or a storage address corresponding to the target I/O sequence, the target I/O sequence comprises at least one instruction, and the at least one instruction is used to access the target data.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the determining the target fingerprint based on the target input/output I/O sequence comprises:
determining the target fingerprint based on a feature of the target I/O sequence and a feature of the target data, wherein
when the target data belongs to a file system, the feature of the target data comprises at least one of the following: metadata of the target data, metadata of the file system, or content of the target data; or
when the target data is a data block or a part of data in the data block, the feature of the target data comprises at least one of metadata of the target data or content of the target data.

### Claim 4 (depends on 3)

The method according to claim 3, wherein the metadata of the file system comprises at least one of the following: identification information of the target data in the file system or identification information of a directory in which the target data is located in the file system.

### Claim 5 (depends on 3)

The method according to claim 3, wherein the determining the target fingerprint based on the feature of the target I/O sequence and the feature of the target data comprises:
determining an entropy value of the content of the target data based on the content of the target data; and
determining the target fingerprint based on the feature of the target I/O sequence and the entropy value of the content of the target data.

### Claim 6 (depends on 1)

The method according to claim 1, wherein the determining the target fingerprint based on the target input/output I/O sequence comprises:
encoding at least one feature of the target I/O sequence, to determine the target fingerprint.

### Claim 7 (depends on 6)

The method according to claim 6, wherein the encoding the at least one feature of the target I/O sequence, to determine the target fingerprint comprises:
determining a first vector based on the at least one feature of the target I/O sequence; and
determining the target fingerprint based on the first vector.

### Claim 8 (depends on 3)

The method according to claim 3, wherein the determining the target fingerprint based on the feature of the target I/O sequence and the feature of the target data comprises:
encoding at least one feature of the target I/O sequence and at least one feature of the target data, to determine the target fingerprint.

### Claim 9 (depends on 8)

The method according to claim 8, wherein the encoding the at least one feature of the target I/O sequence and the at least one feature of the target data, to determine the target fingerprint comprises:
determining a second vector based on the at least one feature of the target I/O sequence and the at least one feature of the target data; and
determining the target fingerprint based on the second vector.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the determining, based on the similarity, that the target I/O sequence is the normal I/O sequence or the ransomware attack I/O sequence comprises:
if a similarity between the target fingerprint and a first attack fingerprint is greater than or equal to a first preset threshold, determining that the target I/O sequence is the ransomware attack I/O sequence, wherein the first attack fingerprint is one of the at least one attack fingerprint; and
if a similarity between the target fingerprint and each of the at least one attack fingerprint is less than the first preset threshold, determining that the target I/O sequence is the normal I/O sequence.

### Claim 11 (depends on 1)

The method according to claim 1, wherein the method further comprises:
when determining that the target I/O sequence is the ransomware attack I/O sequence, adding the target fingerprint to the attack fingerprint library.

### Claim 12 (depends on 11)

The method according to claim 11, wherein before adding the target fingerprint to the attack fingerprint library, the method further comprises:
determining that a similarity between a second attack fingerprint and the target fingerprint is less than a second preset threshold, wherein the second attack fingerprint is an attack fingerprint that is in the at least one attack fingerprint and that has a highest similarity to the target fingerprint, and the second preset threshold is greater than a first preset threshold.

### Claim 13 (depends on 1)

The method according to claim 1, wherein the method further comprises:
determining a first attack I/O sequence based on a first ransomware attack sample in a ransomware attack sample library, wherein the first ransomware attack sample is a ransomware attack sample in the ransomware attack sample library; and
determining a first attack fingerprint based on the first attack I/O sequence, wherein the first attack fingerprint is one of the at least one attack fingerprint.

### Claim 14

A computing device, comprising at least one processor and a memory, wherein the memory is configured to store a computer program, and the computer program comprises program instructions; and
wherein the program instructions, when executed by the at least one processor, cause the computing device to:
determine a target fingerprint based on a target input/output (I/O) sequence, wherein the target I/O sequence is used to access target data;
determine a similarity between an attack fingerprint in an attack fingerprint library and the target fingerprint based on the attack fingerprint library and the target fingerprint, wherein the attack fingerprint library comprises at least one attack fingerprint, and the attack fingerprint is determined based on an attack I/O sequence in a historical ransomware attack; and
determine, based on the similarity, that the target I/O sequence is a normal I/O sequence or a ransomware attack I/O sequence.

### Claim 15 (depends on 14)

The computing device according to claim 14, wherein the causing the computing device to determine the target fingerprint based on the target input/output I/O sequence comprises causing the computing device to:
determine the target fingerprint based on a feature of the target I/O sequence, wherein the feature of the target I/O sequence comprises at least one of an instruction comprised in the target I/O sequence or a storage address corresponding to the target I/O sequence, the target I/O sequence comprises at least one instruction, and the at least one instruction is used to access the target data.

### Claim 16 (depends on 14)

The computing device according to claim 14, wherein the causing the computing device to determine the target fingerprint based on the target input/output I/O sequence comprises causing the computing device to:
determine the target fingerprint based on a feature of the target I/O sequence and a feature of the target data, wherein
when the target data belongs to a file system, the feature of the target data comprises at least one of the following: metadata of the target data, metadata of the file system, or content of the target data; or
when the target data is a data block or a part of data in the data block, the feature of the target data comprises at least one of metadata of the target data or content of the target data.

### Claim 17 (depends on 16)

The computing device according to claim 16, wherein the metadata of the file system comprises at least one of the following: identification information of the target data in the file system or identification information of a directory in which the target data is located in the file system.

### Claim 18 (depends on 16)

The computing device according to claim 16, wherein the causing the computing device to determine the target fingerprint based on the feature of the target I/O sequence and the feature of the target data comprises causing the computing device to:
determine an entropy value of the content of the target data based on the content of the target data; and
determine the target fingerprint based on the feature of the target I/O sequence and the entropy value of the content of the target data.

### Claim 19 (depends on 14)

The computing device according to claim 14, wherein the causing the computing device to determine the target fingerprint based on the target input/output I/O sequence comprises causing the computing device to:
encode at least one feature of the target I/O sequence, to determine the target fingerprint.

### Claim 20 (depends on 19)

The computing device according to claim 19, wherein the causing the computing device to encode the at least one feature of the target I/O sequence, to determine the target fingerprint comprises causing the computing device to:
determine a first vector based on the at least one feature of the target I/O sequence; and
determine the target fingerprint based on the first vector.
