CN213751121U - Attack testing device aiming at fingerprint identification self-learning algorithm - Google Patents
Attack testing device aiming at fingerprint identification self-learning algorithm Download PDFInfo
- Publication number
- CN213751121U CN213751121U CN202023282509.XU CN202023282509U CN213751121U CN 213751121 U CN213751121 U CN 213751121U CN 202023282509 U CN202023282509 U CN 202023282509U CN 213751121 U CN213751121 U CN 213751121U
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- testing device
- attack
- learning algorithm
- wire
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The utility model discloses an attack testing arrangement to fingerprint identification self-learning algorithm relates to fingerprint identification's security performance test technical field, has solved current testing arrangement and can't test fingerprint self-learning algorithm's security performance. Including fingerprint sensor, fingerprint debugging board that connect gradually and place stage body and screen panel structure, fingerprint sensor sets up on placing the stage body, places the stage body setting in the screen panel structure. The utility model discloses can contrast out the quality of multiple fingerprint identification self-learning algorithm on the security performance fast, this device structure is succinct, it is convenient to use, and maneuverability is strong.
Description
Technical Field
The utility model relates to a fingerprint identification's security performance test technical field especially relates to an attack testing arrangement to fingerprint identification self-learning algorithm.
Background
Among all the biometric technologies, the fingerprint identification technology is the most mature and widely applied biometric technology at present, and the fingerprint identification device has begun to be widely applied to various entrance guard security intelligent locks, fingerprint identification electronic padlocks and the like. Before fingerprint equipment is used, registered fingerprints need to be registered, however, fingerprint characteristic points extracted in limited registration are not complete, in order to improve the speed and accuracy of fingerprint identification which is most concerned with the use of users (especially poor fingerprint users), fingerprint manufacturers add a fingerprint self-learning module or algorithm into a fingerprint identification system, namely in the fingerprint identification process, partial fingerprints which are not recorded before are fused into a fingerprint database after successful identification, so as to form a new fingerprint database, so that the fingerprint data is more complete, and more fingerprint data are collected after each identification is unlocked, which means that the fingerprints are more and more quickly identified and the accuracy is higher and higher as time goes on.
How to distinguish the pseudo feature points formed by foreign matters, dirt, unsatisfactory image processing effect and the like is one of the difficulties which need to be overcome by the fingerprint self-learning module or algorithm. Most of the existing testing methods or devices only perform simple function tests on the fingerprint self-learning module or algorithm, can reflect whether the fingerprint self-learning realizes the function or not, but cannot reflect whether the safety performance of the fingerprint self-learning module or the fingerprint self-learning algorithm is good or bad.
SUMMERY OF THE UTILITY MODEL
The to-be-solved technical problem of the utility model lies in that can not reflect its security performance's good or bad defect to prior art, provides an attack testing arrangement to fingerprint identification self-learning algorithm.
The utility model provides a technical scheme that its technical problem adopted is: an attack testing device aiming at a fingerprint identification self-learning algorithm comprises a fingerprint sensor, a fingerprint debugging plate, a testing module, a placing table body and a mesh enclosure structure.
Furthermore, the fingerprint sensor, the fingerprint debugging board and the testing module are sequentially connected, the fingerprint sensor is arranged on the placing table body, and the placing table body is arranged in the mesh enclosure structure; when a finger is pressed to the fingerprint sensor from the mesh enclosure structure from top to bottom, the fingerprint sensor can acquire a fingerprint image of the finger; the fingerprint debugging board is used for debugging the fingerprint image before testing and acquiring current data; the testing module verifies the safety performance of the fingerprint identification self-learning algorithm by identifying the debugged fingerprint image.
Further, fingerprint sensor sets up on placing the stage body, it sets up in the screen panel structure to place the stage body. The finger from top to bottom from the screen panel structure press to fingerprint sensor, fingerprint sensor gathers the fingerprint image of this finger, the fingerprint image warp fingerprint debugging board transmits extremely test from the test module.
Further, the mesh enclosure structure comprises at least one metal wire, a plurality of fixing pins and a base. The metal wire is connected in a plurality of on the fixed needle, fixed needle all with base fixed connection.
Preferably, the diameter of the wire is 0.05-0.1 mm.
Preferably, the metal wire is a copper wire.
Further, the metal wire is connected to the fixing needle to form different pattern lines, and the pattern lines are straight line cross lines, straight line parallel lines, curve lines or wavy line lines.
Furthermore, one end of the fixing needle is provided with a hole through which the metal wire can penetrate, and the other end of the fixing needle is welded, riveted or inserted with the base; or the fixing needle and the base are of an integrated structure.
Further, the base and the placing table body are of independent structures or are connected through a fixing device.
Further, the placing table body is connected with the fingerprint sensor through a fixing structure or an anti-skid structure.
Furthermore, the fingerprint sensor is connected with the fingerprint debugging plate through a flexible circuit board or a lead.
Furthermore, the fingerprint debugging board is connected with the test module through a USB line.
Implement the utility model discloses an attack testing arrangement's technical scheme has following advantage or beneficial effect:
the utility model discloses utilize filament simulation fingerprint striae or erect the line, make the pseudo-characteristic point of fingerprint, attack test fingerprint self-learning algorithm, verify its function and security performance. The device can test the function of the fingerprint self-learning algorithm and can also detect the safety performance of the algorithm; the metal wire in the device has strong plasticity, can be transformed into various pattern lines for testing, can simulate fingerprint lines and is not easy to deform, so that different algorithms are tested by using fixed patterns in the test, and the advantages and disadvantages of the safety performance of the algorithms can be quickly compared; in addition, the device has the advantages of simple structure, convenience in use and strong operability.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained without inventive work, and in the drawings:
fig. 1 is a schematic diagram of a connection relationship between an attack testing device and a fingerprint debugging board and a testing module according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an attack testing apparatus according to an embodiment of the present invention;
fig. 3 is a graph of the pattern of a wire according to an embodiment of the present invention;
FIG. 4 is a diagram of a fingerprint image collected without using a testing device in an embodiment of the present invention;
fig. 5 is the fingerprint image that is gathered after the testing device is used in the embodiment of the present invention.
1. A fingerprint sensor; 2. a fingerprint debugging board; 3. a test module; 4. placing the table body; 5. a mesh enclosure structure; 50. a metal wire; 51. a fixing pin; 52. a base.
Detailed Description
In order to make the objects, solutions and advantages of the present invention more apparent, the various embodiments to be described hereinafter will be referred to the accompanying drawings, which form a part hereof, and in which are shown by way of illustration various embodiments in which the invention may be practiced. It is to be understood that other embodiments may be utilized and structural and functional modifications may be made to the embodiments set forth herein without departing from the scope and spirit of the present invention. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
As shown in figure 1, the attack testing device aiming at the fingerprint identification self-learning algorithm comprises a fingerprint sensor 1, a fingerprint debugging plate 2 and a testing module 3, wherein the fingerprint sensor 1, the fingerprint debugging plate 2 and the testing module 3 are sequentially connected, and the attack testing device further comprises a placing table body 4 and a mesh enclosure structure 5. Fingerprint sensor 1 sets up on placing stage body 4, places stage body 4 and sets up in screen panel structure 5. The net cover structure 5 in the attack testing device is used for manufacturing fingerprint pseudo-characteristic points, and fingerprint images containing the pseudo-characteristic points are collected through the fingerprint sensor 1 to attack and test a fingerprint self-learning algorithm so as to verify the function and the safety performance of the fingerprint self-learning algorithm. Specifically, when the finger from top to bottom presses to fingerprint sensor 1 from mesh enclosure structure 5, fingerprint sensor 1 can gather the fingerprint image of this finger, and fingerprint debugging board 2 is used for debugging before testing fingerprint image and the collection of electric current data (such as consumption electric current) (because the fingerprint image definition and the difference of how much of noise of different fingerprint sensor collection, therefore need to carry out data acquisition and the corresponding debugging before testing to fingerprint image), and test module 3 verifies the security performance of fingerprint identification self-learning algorithm through the fingerprint image after the discernment is debugged. The test module 3 is provided with a plurality of fingerprint identification self-learning algorithms, the test module 3 is a carrier for installing the fingerprint identification self-learning algorithms and a carrier (such as a computer) for displaying test results, and the fingerprint identification self-learning algorithms are self-existing technologies or existing technologies and are not described herein again.
As shown in fig. 2, the mesh enclosure structure 5 includes at least one wire 50, a plurality of fixing pins 51, and a base 52. One end of each fixing pin 51 is provided with a hole through which the metal wire 50 can penetrate, and the other end of each fixing pin is fixedly connected with the base 52 in a welding, riveting or inserting mode; on the other hand, the fixing pin 51 and the base 52 may be formed as an integral structure for convenience of processing. The wire 50 passes through part or all of the holes and is detachably connected with the fixing pin 51 by binding, wherein the wire can be a long wire or a plurality of short wires.
Preferably, the wire 50 has a diameter of 0.05-0.1 mm. The metal wire has strong plasticity, can be transformed into various pattern lines for testing, can simulate fingerprint lines and is not easy to deform, thus the device is a better material for detecting. The wire 50 in this embodiment is a copper wire. As shown in fig. 3, the wire 50 is connected to the fixing pin 51 to form different patterns, which may be straight cross patterns or straight parallel patterns of straight lines, or curved lines or wavy lines. Moreover, the base 52 and the placing table body 4 are independent structures or are connected through a fixing device (such as a connecting piece and a connecting rod); the placing table body 4 is fixedly connected with the fingerprint sensor 1 through a fixing structure (such as a buckle connection or a fixing part), and can also be connected with other anti-skid structures (such as a cushion for increasing friction) which can prevent the fingerprint sensor 1 from sliding off from the placing table body 4; the fingerprint sensor 1 is connected with the fingerprint debugging plate 2 through a flexible circuit board or a lead. The fingerprint debugging board 2 is connected with the testing module 3 through a USB line.
The specific embodiment is as follows: the testing module 3 stored in the computer is started, the computer enters a registration mode, a finger presses the fingerprint sensor to register a fingerprint A in advance, at the moment, the image of the registered fingerprint can be checked, and the image of the registered fingerprint is shown in figure 4. The testing begins, fixes fingerprint sensor 1 at placing stage body 4, and at this moment, the superfine wire (select arbitrary pattern line of straight line cross line, straight line parallel line, curve line and wave line) of screen panel structure 5 covers on the fingerprint sensor surface, opens test module 3's fingerprint comparison mode, and the finger pushes down fingerprint sensor, gathers fingerprint image and registers fingerprint A and compares, can show the fingerprint image and the comparison result of comparison in the fingerprint test software, and the fingerprint map of comparison is shown in figure 5.
In the fingerprint image of fig. 4, the white stripes are natural horizontal stripes (i) or vertical stripes (ii) on the fingerprint, and are ubiquitous in the fingerprint. The appearance of the horizontal and vertical fingerprint lines enables the continuous and smooth fingerprint lines to be interrupted, and characteristic points such as short lines, isolated points and the like are formed. The testing device is matched with the ultra-fine diameter metal copper wire, so that the ultra-fine diameter metal copper wire is parallel or crossed at different angles, transverse and vertical lines in the fingerprint can be simulated, pseudo characteristic points are formed, and the safety performance of the fingerprint self-learning algorithm is tested. The white stripes (c) and (c) in the fingerprint collected in fig. 4 are the transverse stripes simulated by the superfine copper wires, which intersect with the original natural transverse and vertical stripes of the fingerprint, so that the smooth fingerprint of the local area of the fingerprint is broken, and new short stripes, isolated points, intersection points and other pseudo feature points are formed. Under the condition that most of the identified fingerprints have the characteristic points of the registered fingerprint A and new characteristic points appear in local areas, the self-learning algorithm probably considers that the newly appeared pseudo characteristic points are the part of the registered fingerprint A which is not recorded, and then the pseudo characteristic points are added into the fingerprint database of the fingerprint A. Therefore, the device is used for detecting whether the self-learning algorithm has the safety problem.
The attack test results before and after the self-learning algorithm is detected by the device are as follows: before the self-learning algorithm is upgraded, the device uses a plurality of ultra-fine metal wires to simulate fingerprint lines, and uses unregistered fingerprints to carry out comparison attack test, wherein the test comparison is carried out for 450 times, 2 times of comparison is successful, and the comparison success rate is 0.44%. Under the condition that the attack test result is not ideal, after the self-learning algorithm is upgraded, the same device and unregistered fingerprints are used for comparison attack test, the test comparison is carried out for 1000 times, the comparison is successful for 0 time, the comparison success rate is 0%, and the algorithm safety performance is obviously improved.
To sum up, the utility model discloses utilize filament simulation fingerprint striae or erect the line, make the pseudo-characteristic point of fingerprint, attack test fingerprint self-learning algorithm, verify its function and security performance. The device can test the function of the fingerprint self-learning algorithm and can also detect the safety performance of the algorithm; the metal wire in the device has strong plasticity, can be transformed into various pattern lines for testing, can simulate fingerprint lines and is not easy to deform, so that different algorithms are tested by using fixed patterns in the test, and the advantages and disadvantages of the safety performance of the algorithms can be quickly compared; in addition, the device has the advantages of simple structure, convenience in use and strong operability.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the invention. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from the essential scope thereof. Therefore, the present invention is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of the present application belong to the protection scope of the present invention.
Claims (10)
1. An attack testing device aiming at a fingerprint identification self-learning algorithm comprises a fingerprint sensor (1), a fingerprint debugging plate (2), a testing module (3), a placing table body (4) and a mesh enclosure structure (5);
the fingerprint sensor (1), the fingerprint debugging plate (2) and the testing module (3) are connected in sequence; the fingerprint sensor (1) is arranged on the placing table body (4), and the placing table body (4) is arranged in the mesh enclosure structure (5);
a finger is pressed to the fingerprint sensor (1) from top to bottom from the mesh enclosure structure (5), and the fingerprint sensor (1) can collect a fingerprint image of the finger; the fingerprint debugging plate (2) is used for debugging the fingerprint image before testing and acquiring current data; the testing module (3) verifies the safety performance of the fingerprint identification self-learning algorithm by identifying the debugged fingerprint image.
2. The attack testing device according to claim 1, characterized in that the mesh structure (5) comprises at least one wire (50), a plurality of fixing pins (51) and a base (52);
the metal wire (50) is connected to the plurality of fixing needles (51), and the fixing needles (51) are fixedly connected with the base (52).
3. The attack testing device according to claim 2, characterised in that the diameter of the wire (50) is 0.05-0.1 mm.
4. The attack testing device according to claim 3, characterised in that the metal wire (50) is a copper wire.
5. The attack testing device according to claim 2 or 3, characterized in that the connection of the wire (50) to the fixing pin (51) enables different patterns to be formed;
the pattern lines are straight line cross lines, straight line parallel lines, curve lines or wave line lines.
6. The attack testing device according to claim 4, wherein one end of the fixing pin (51) is provided with a hole for the metal wire (50) to penetrate through, and the other end of the fixing pin is welded, riveted or inserted with the base (52);
or the fixing needle (51) and the base (52) are of an integral structure.
7. Attack testing device according to claim 6, characterised in that the base (52) is a separate structure from the placement stage (4) or is connected by fixing means.
8. Attack testing device according to claim 7, characterised in that the placement stage (4) is connected to the fingerprint sensor (1) by means of a fixed or non-slip structure.
9. The attack testing device according to claim 1, characterized in that the fingerprint sensor (1) and the fingerprint debugging plate (2) are connected by a flexible circuit board or a wire.
10. Attack testing device according to claim 1, characterized in that the fingerprint debugging board (2) and the testing module (3) are connected by a USB cable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202023282509.XU CN213751121U (en) | 2020-12-29 | 2020-12-29 | Attack testing device aiming at fingerprint identification self-learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202023282509.XU CN213751121U (en) | 2020-12-29 | 2020-12-29 | Attack testing device aiming at fingerprint identification self-learning algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN213751121U true CN213751121U (en) | 2021-07-20 |
Family
ID=76837499
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202023282509.XU Active CN213751121U (en) | 2020-12-29 | 2020-12-29 | Attack testing device aiming at fingerprint identification self-learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN213751121U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116311628A (en) * | 2023-05-23 | 2023-06-23 | 合肥智辉空间科技有限责任公司 | Method and system for detecting safety performance of intelligent door lock |
-
2020
- 2020-12-29 CN CN202023282509.XU patent/CN213751121U/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116311628A (en) * | 2023-05-23 | 2023-06-23 | 合肥智辉空间科技有限责任公司 | Method and system for detecting safety performance of intelligent door lock |
| CN116311628B (en) * | 2023-05-23 | 2023-08-11 | 合肥智辉空间科技有限责任公司 | Method and system for detecting safety performance of intelligent door lock |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN213751121U (en) | Attack testing device aiming at fingerprint identification self-learning algorithm | |
| CN105528117B (en) | A kind of acquisition methods and device of touch screen scan frequency | |
| CN106567220A (en) | Washing machine having cloth material identification function and control method thereof | |
| CN110119680B (en) | Automatic error checking system of regulator cubicle wiring based on image recognition | |
| CN104897687B (en) | The detecting system and method for probe pin trace position | |
| CN213091818U (en) | PCBA function automatic test system | |
| CN109521015B (en) | Visual identification and detection system for automobile fuse box | |
| CN105999655B (en) | The method of counting and system of push-up test | |
| CN110082620A (en) | A kind of charging pile working state detecting method and device | |
| CN106597261A (en) | Wafer test system | |
| CN110147751A (en) | A kind of method and device of fingerprint detection | |
| CN109886162A (en) | Fingerprint authentication method and relevant apparatus | |
| CN110346704A (en) | Determination method, apparatus, equipment and the storage medium of test file in board test | |
| CN110235145A (en) | Fingerprint identification method, device, electronic equipment and storage medium | |
| TWI423145B (en) | Method for identifying fingerprint image | |
| CN101430722A (en) | Test point layout detection method | |
| CN107703395A (en) | A kind of pulse test system and method for testing for vehicle-carrying display screen | |
| CN110301892A (en) | A kind of detection method and Related product based on hand vein recognition | |
| CN112067919B (en) | Automatic cable type identification device and automatic test method | |
| CN109343019A (en) | A kind of Georadar Data means of interpretation and device | |
| CN105933506A (en) | Mobile terminal unlocking method, device, mobile terminal and earphone | |
| JP5103715B2 (en) | Method and program for identifying source of electromagnetic interference signal | |
| CN107041731A (en) | A kind of stomach oesophagus gas reflux detection method and device | |
| US6708143B1 (en) | Verification coverage method | |
| US8107718B2 (en) | Method, system, and apparatus for use in locating a structure in an integrated circuit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |