Man-machine identification method, device, server, client and storage medium

A human-machine identification and client-side technology, applied in the information field, can solve the problem of inability to accurately identify machine attacks, attacks, and deceive servers, etc., to achieve reliable user activity, prevent spike products, and prevent attacks.

Active Publication Date: 2021-06-11
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The main problem of existing method is: (1) action data such as mouse, keyboard, gesture and / or gyroscope can be forged or tampered, machine attack obtains the behavior action data of mouse and keyboard gesture conforming to format by forgery or tampering, cheats server, The server cannot accurately identify and distinguish, and cannot intercept
(2) The device can be forged. The attacker deceives the server by forging the device data, so that the server cannot accurately identify the machine attack. For example, the attacker can forge the browser version and other information

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Man-machine identification method, device, server, client and storage medium
  • Man-machine identification method, device, server, client and storage medium
  • Man-machine identification method, device, server, client and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0055] According to an embodiment of the method for identifying a human-machine based on a proof of work applied to a client in the present invention, the pre-deployed proof of work algorithm includes a proof of work algorithm that has undergone encryption and / or obfuscation.

[0056] The PoW algorithm of obfuscated encryption can be pre-deployed on the client. Due to PoW algorithm encryption, code obfuscation, and the limited computing power of a single device, attackers cannot use GPU (Graphic Processing Unit, Graphics Processing Unit) and other acceleration methods to simulate a large number of devices on a single device. Unlike a CPU, a GPU is a chip designed specifically to handle graphics tasks. The GPU contains more processing units than the CPU and has greater bandwidth, enabling it to exert greater performance in multimedia processing. In addition, in terms of hardware design, a CPU consists of a few cores optimized for sequential serial processing, while a GPU consist...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention proposes a workload-proof-based human-computer identification method, device, server, client, and computer-readable storage medium, wherein the workload-based human-computer identification method includes: receiving from the client terminal generated by a workload-proof algorithm A result set and client behavior data, wherein the result set includes the workload situation corresponding to the client behavior data; and human-computer identification is performed according to the result set and the client behavior data. The embodiment of the present invention can be used to prevent machine attacks on the app and web pages, such as preventing robots from posting, swiping points, and posting advertisements, and at the same time can provide protection against spike-grabbing behaviors and prevent machines from spike-killing products; in addition, the embodiments of the present invention The user's real stay time on the page is recorded, and a more reliable user activity can be obtained. The obtained user stay time has greater accuracy, and effectively prevents attacks of forged data.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to a workload proof-based human-computer identification method, device, server, client and computer-readable storage medium. Background technique [0002] With the development of artificial intelligence technology, it is difficult for traditional verification codes to resist machine attacks caused by OCR (Optical Character Recognition, Optical Character Recognition) and coding platforms. At present, new methods are urgently needed to fight against machine attacks caused by machine attacks. Loss. Typical machine attacks include credential stuffing, fleece extraction, machine registration, machine ordering, etc. Among them, the collision database has caused serious losses to many well-known websites, and machine registration, machine ordering, machine ticket grabbing, and cash grabbing are all pervasive. For example: because traditional verification codes cannot resist ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F21/31H04L29/06
CPCG06F21/316G06F2221/2133H04L63/1416
Inventor 杨伟光
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products