CN106712928A - Big data rainbow table based decryption method and device - Google Patents
Big data rainbow table based decryption method and device Download PDFInfo
- Publication number
- CN106712928A CN106712928A CN201611147432.0A CN201611147432A CN106712928A CN 106712928 A CN106712928 A CN 106712928A CN 201611147432 A CN201611147432 A CN 201611147432A CN 106712928 A CN106712928 A CN 106712928A
- Authority
- CN
- China
- Prior art keywords
- rainbow table
- rainbow
- gpu
- task
- decryption
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/06—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols the encryption apparatus using shift registers or memories for block-wise or stream coding, e.g. DES systems or RC4; Hash functions; Pseudorandom sequence generators
- H04L9/0643—Hash functions, e.g. MD5, SHA, HMAC or f9 MAC
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3215—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a plurality of channels
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3236—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using cryptographic hash functions
- H04L9/3242—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using cryptographic hash functions involving keyed hash functions, e.g. message authentication codes [MACs], CBC-MAC or HMAC
Abstract
The invention discloses a big data rainbow table based decryption method and device. The decryption method comprises the steps that rainbow table tasks are allocated to n GPU (Graphic Processing Unit) computing nodes, wherein n is an integer which is greater than 1; each GPU computing node generates a rainbow table; index grouping is performed on chain end nodes of Hash chains in the generated rainbow tables, and sorting the chain end nodes in each group; and in the index grouped and sorted rainbow tables, firstly performing index searching on a ciphertext to be decrypted, and then executing binary searching so as to acquire a corresponding plaintext to complete decryption. For letter-number combination passwords with 1-12 bits, the Hash chains in the rainbow tables can be generated in a parallel manner via a plurality of GPUs by using an encryption result ciphertext, so that the generation speed of the rainbow tables is greatly improved. In addition, index sorting is performed on the generated rainbow tables, so that the rainbow table searching time in a decryption stage is greatly shortened, and the decryption time is greatly shortened.
Description
Technical field
The present invention relates to password backward recovery technical field, more particularly to a kind of decryption method based on big data rainbow table
And device.
Background technology
With the fast development of internet, network information security requirement more and more higher.In order to ensure safety, generally using close
Code encryption and decryption technology.The encryption technology and means of various agreements emerge in an endless stream in internet, occur in that such as MD5, SHA1,
The AESs such as LM, NTLMHASH and MD4.For various AESs implement after obtain ciphertext, using decryption technology come
Ciphertext is cracked to obtain in plain text.
At present, for simple password and cryptographic system, password cracking can be by the way of Brute Force.And for compared with
Complicated password and cryptographic system, such as, for the password more than 8, the amount of calculation of Brute Force is very big.Generally using color
Rainbow table is cracked.Rainbow table is a huge Hash precalculated for various possible numerals, monogram
(hash) set of value, rainbow table technology is exactly to set up a corresponding Hash table between source data and encryption data, is so existed
Pass through compare, inquire about or certain computing after obtaining encryption data, source data can be quickly positioned, so that by rainbow table
Construction and lookup, being capable of decryption acquisition plaintext.
However, rainbow table is used as a kind of Hash table of compression, for password more long, rainbow table often takes up room huge
Greatly, it is very long to crack the time, in some cases, beyond unit memory range, even if or be disclosure satisfy that on cluster storage but
It is that the generation time is oversize, it is impossible to which satisfaction is actually needed.Further, since rainbow list file is very big, and during lookup is cracked, consumption
When efficiency very long it is very low.Even if in the presence of some commercial rainbow tables, the password of less than 9 can only be often cracked, and crack
Accuracy rate only has 80% or so, cracks the time long, it is difficult to which satisfaction is actually needed.
The content of the invention
To overcome problem present in correlation technique, the present invention provide a kind of decryption method based on big data rainbow table and
Device, the password of the digital alphabet combination for 1-12, using the encrypted result ciphertext for obtaining, can be by using multiple
Hash chain in GPU parallel generation rainbow tables greatly improves rainbow table formation speed, and rainbow table to generating carries out rope
Ejectment sequence, greatly shortens the rainbow table search time of decryption phase, so as to greatly shorten decryption time.
A kind of first aspect according to embodiments of the present invention, there is provided decryption method based on big data rainbow table, including：Will
Rainbow table task distributes to n GPU calculate node, and wherein n is the integer more than 1；Coloured silk of each GPU calculate node according to distribution
Rainbow table task generates a rainbow table；The joint of the chain tail of the hash chain in the rainbow table of generation is indexed packet, to packet
Interior joint of the chain tail is ranked up；In the rainbow table of indexed packet and sequence, index is first carried out to ciphertext to be decrypted and is looked into
Binary chop is looked for and then performs, to obtain corresponding completion decryption in plain text.
According to one embodiment of present invention, rainbow table task is distributed into n GPU calculate node includes：According in plain text
Span, the lookup success rate of rainbow table the size of rainbow table task is set, rainbow table task includes multiple hash chains
Task, each hash chain task will generate a hash chain；The rainbow table task is distributed according to the quantity of hash chain task
To n GPU calculate node.
According to one embodiment of present invention, in the case where the quantity of hash chain task is for m, m/n=x+y, wherein, x
It is the business that m is obtained divided by n, y is remainder, m is that integer more than 1, x are integer more than 0, and y is integer, and the rainbow table is appointed
N GPU calculate node is distributed in business to be included：Each the GPU calculate node being first in n GPU calculate node distributes x Hash
Chain task；Then the preceding y GPU remaining y hash chain task order being reallocated in n GPU calculate node is calculated
Node, is that each the GPU calculate node in preceding y GPU calculate nodes distributes a hash chain task.
According to one embodiment of present invention, the joint of the chain tail of the hash chain in the rainbow table of generation is indexed point
Group, the joint of the chain tail in packet is ranked up including：The magnitude range of the binary numeral of the joint of the chain tail according to hash chain
To be indexed packet to rainbow table；To each packet in hash chain joint of the chain tail according to binary numeral size order
It is ranked up.
According to one embodiment of present invention, ciphertext to be decrypted passes through LM, MD4, NTLSHASH, MD5 or SHA1 algorithm
Encryption, the password corresponding with ciphertext to be decrypted is 1-12.
A kind of second aspect according to embodiments of the present invention, there is provided decryption device based on big data rainbow table, including：n
Individual GPU calculate nodes, are allocated rainbow table task, and each GPU calculate node generates a rainbow table, and n is the integer more than 1；
Rainbow table index sequencing unit, rope is carried out for the joint of the chain tail to the hash chain in the n rainbow table of GPU calculate nodes generation
Draw packet, the joint of the chain tail in packet is ranked up；Searching unit, for it is indexed packet and sequence rainbow table in,
Index search is first carried out to ciphertext to be decrypted and then binary chop is performed, to obtain corresponding completion decryption in plain text.
According to one embodiment of present invention, the decryption device based on big data rainbow table also includes file system, is used for
Rainbow table task, n rainbow table of GPU calculate nodes generation of storage are distributed to n GPU calculate node.
According to one embodiment of present invention, file system includes：Rainbow table generates logging unit, for being each
GPU calculate nodes set rainbow table generation data parameters, and the table generation of write-in rainbow is marked, and rainbow table generation mark is for indicating coloured silk
Whether the generation of rainbow table succeeds；Daily record inspection unit, for checking rainbow table generation mark, if the generation mark instruction of rainbow table is color
The generation of rainbow table is unsuccessful, calls corresponding GPU calculate nodes to continue to generate rainbow table.
According to one embodiment of present invention, file system also includes：GPU dispensing units, for the value according to plaintext
Scope, the lookup success rate of rainbow table are that each GPU calculate node sets calculating parameter, data transfer and generating algorithm.
According to one embodiment of present invention, the decryption device based on big data rainbow table also includes storage array, is used for
The indexed packet of storage and the rainbow table of sequence.
Therefore, embodiments of the invention provide a kind of decryption method based on big data rainbow table, including：By rainbow
Table task distributes to n GPU calculate node, wherein, the n is the integer more than 1；Each GPU calculate node generates a coloured silk
Rainbow table；The joint of the chain tail of the hash chain in the rainbow table of generation is indexed packet, the joint of the chain tail in packet is arranged
Sequence；In the rainbow table of indexed packet and sequence, first carry out index search and then perform two points for ciphertext to be decrypted and look into
Look for, to obtain corresponding completion decryption in plain text.The decryption method based on big data rainbow table of embodiments of the invention can lead to
Cross using the hash chain in multiple GPU calculate node parallel generation rainbow tables to greatly improve rainbow table formation speed, and lead to
Cross and be indexed sequence to the rainbow table for generating and greatly shorten rainbow table search time of decryption phase, so as to greatly shorten
Decryption time.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary and explanatory, not
Can the limitation present invention.
Brief description of the drawings
Accompanying drawing herein is merged in specification and constitutes the part of this specification, shows and meets implementation of the invention
Example, and be used to explain principle of the invention together with specification.
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, for those of ordinary skill in the art
Speech, without having to pay creative labor, can also obtain other accompanying drawings according to these accompanying drawings.
Fig. 1 is that the flow of the decryption method based on big data rainbow table for providing according to one embodiment of present invention is illustrated
Figure；
Fig. 2 is the structural representation of the decryption device based on big data rainbow table for providing according to one embodiment of present invention
Figure；
Fig. 3 is the structural schematic block diagram of the file system for providing according to one embodiment of present invention.
Specific embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in implementation method do not represent and the consistent all implementation methods of the present invention.Conversely, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects being described in detail in claims, of the invention.
Fig. 1 is that the flow of the decryption method based on big data rainbow table for providing according to one embodiment of present invention is illustrated
Figure.As shown in figure 1, the decryption method based on big data rainbow table according to an embodiment of the invention includes：Step S1, will
Rainbow table task distributes to n GPU (Graphic Processing Unit, graphics processing unit) calculate node, wherein, n is
Integer more than 1；Step S2, each GPU calculate node generates a rainbow table according to the rainbow table task of distribution；Step S3,
The joint of the chain tail of the hash chain in the rainbow table of generation is indexed packet, the joint of the chain tail in packet is ranked up；Step
Rapid S4, in the rainbow table of indexed packet and sequence, index search is first carried out to ciphertext to be decrypted and then two points are performed and looked into
Look for, to obtain corresponding completion decryption in plain text.
Specifically, above-mentioned steps S1 can include：The lookup success rate of span, rainbow table according to plaintext is set
The size of rainbow table task, rainbow table task includes multiple hash chain tasks, and each hash chain task will generate a hash chain；
Rainbow table task is distributed into n GPU calculate node according to the quantity of hash chain task.
As an example it is assumed that the quantity of hash chain task is m, m/n=x+y, wherein, x is the business that m is obtained divided by n, and y is
Remainder, m is that integer more than 1, x are integer more than 0, and y is integer.According to one embodiment of present invention, above-mentioned steps S1
Can include：Each the GPU calculate node being first in n GPU calculate node distributes x hash chain task；Then by residue
Y hash chain task order be reallocated in n GPU calculate node preceding y GPU calculate nodes, be preceding y GPU meters
Each GPU calculate node in operator node distributes a hash chain task.
Specifically, above-mentioned steps S3 can include：The magnitude range of the binary numeral of the joint of the chain tail according to hash chain
To be indexed packet to rainbow table；To each packet in hash chain joint of the chain tail according to binary numeral size order
It is ranked up.
Embodiments in accordance with the present invention, ciphertext to be decrypted can be by LM, MD4, NTLSHASH, MD5 or SHA1 algorithm
Encryption, the password corresponding with ciphertext to be decrypted can be 1-12.
Fig. 2 is the decryption device based on big data rainbow table for providing according to one embodiment of present invention.Such as Fig. 2 institutes
Show, the decryption device is distributed architecture, including：N GPU calculate node, is allocated rainbow table task, each GPU meters
Operator node generates a rainbow table according to the rainbow table task of distribution, and n is the integer more than 1；Rainbow table index sequencing unit 10,
Packet is indexed for the joint of the chain tail to the hash chain in the n rainbow table of GPU calculate nodes generation, to the chain in packet
Tail node is ranked up；Searching unit 20, in the rainbow table of indexed packet and sequence, first being held to ciphertext to be decrypted
Binary chop is searched and then performed in line index, and decryption is completed to obtain corresponding plaintext.
According to one embodiment of present invention, as shown in Fig. 2 the decryption device based on big data rainbow table also includes file
System 30, for distributing rainbow table task, n rainbow table of GPU calculate nodes generation of storage to n GPU calculate node.According to
One embodiment of the present of invention, file system 30 can be Hadoop distributed file systems stores the rainbow table of generation.
According to one embodiment of present invention, as shown in figure 3, file system 30 can include：Rainbow table generation daily record note
Record unit 301, for setting rainbow table generation data parameters, write-in rainbow table generation mark, rainbow for each GPU calculate node
Whether table generation mark succeeds for indicating rainbow table to generate；Daily record inspection unit 302, for checking rainbow table generation mark,
If generation mark indicates the generation of rainbow table unsuccessful, corresponding GPU calculate nodes are called to continue to generate rainbow table.
According to one embodiment of present invention, as shown in figure 3, file system 30 can also include：GPU dispensing units 303,
It is that each GPU calculate node sets calculating parameter, data biography for the span according to plaintext, the lookup success rate of rainbow table
Defeated and generating algorithm.
According to one embodiment of present invention, the decryption device based on big data rainbow table can also include storage array
40, the rainbow table for storing indexed packet and sequence.
According to one embodiment of present invention, file system 30, rainbow table index sequencing unit 10 and searching unit 20 can
To be integrated in same system.For example, file system 30, rainbow table index sequencing unit 10 and searching unit 20 can be integrated in
In same main frame or server.
In view of the size of rainbow table will be tens TB grades, the system stores warp using disk array as storage device
Index packet and the rainbow table of sequence.
Specifically, disk array can be combined into a huge disk group of capacity by the relatively inexpensive disk of many prices,
The whole disk system efficiency of addition effect promoting produced by data is provided using indivedual disks.Using this technology, data are cut
Many sections are cut into, are stored in respectively on each hard disk.Disk array can also utilize the sight of parity check (Parity Check)
Read, in an array during any one hard disk failure, can still read data, in data reconstruction, put again after data are computed
In entering new hard disk.Disk array supports the memory capacity of tens more than T at present, disclosure satisfy that the demand of system.
In addition, the computation budget amount of rainbow table is big, the time is generated under the platform of unit oversize, it is contemplated that need decades, this
The decryption device of invention is the distributed architecture based on distribution GPU, and Distributed Calculation is carried out using multiple GPU, multiple
GPU concurrently generates rainbow table, can overcome the limitation of storage capacity and formation speed.
GPU English full name Graphic Processing Unit (graphics processing unit), GPU from the date of birth just with
Surmount the speed development of Moore's Law, operational capability is constantly lifted.GPU is gradually from by some special fixed-function units
To based on general-purpose computational resources, fixed-function unit is the special parallel processor of (Fixed Function Unit) composition
Auxiliary framework transformation.
In general the suitable computing that is adapted to GPU computings is intensive, highly-parallel, control is simple and a point multiple stages hold
OK, meet these conditions or the application program of similar characteristics can be rewritten into, it becomes possible to property higher is obtained on GPU
Energy.GPU general-purpose computations generally use CPU+GPU heterogeneous schemas, are responsible for performing complex logic treatment and issued transaction etc. no by CPU
It is adapted to the calculating of data parallel, the large-scale data parallel computation of computation-intensive is responsible for by GPU.This powerful places of utilization GPU
Reason ability and high bandwidth make up the not enough calculation of cpu performance to play computer Potential performance, are suppose in cost and sexual valence
There is significantly advantage in face.
In an embodiment of the present invention, according to plaintext span and the lookup success rate of rainbow table set rainbow
The size of table task.Algorithm and character set scope can be configured.Rainbow table task can include multiple hash chain tasks, often
Individual hash chain task will generate a hash chain.Due to each hash chain task of rainbow table calculating and generation be it is independent,
There is natural concurrency in the execution of each hash chain task, thus easily for multiple GPU distributes parallel task.
The decryption side based on big data rainbow table according to an embodiment of the invention is briefly described with reference to Fig. 1 to Fig. 3
How method and decryption device are decrypted.
(1) the rainbow table generating process of the distributed type assemblies based on GPU
First, rainbow table task is distributed to n GPU calculate node by file system 30 according to the quantity of hash chain task,
And the lookup success rate of the span, rainbow table in GPU dispensing units according to plaintext is set for each GPU calculate node
Calculating parameter, data transfer and generating algorithm, for each GPU calculate node sets in rainbow table generation logging unit 301
Put rainbow table generation data parameters and a rainbow table generation mark logflags is set, rainbow table generation mark logflags's
Initial value is 0.
As an example it is assumed that the quantity of hash chain task is m, m/n=x+y, wherein, x is the business that m is obtained divided by n, and y is
Remainder, m is that integer more than 1, x are integer more than 0, and y is integer.In this way, the dispatching method that sub- rainbow meter is calculated is as follows：
1) each the GPU calculate node being first in n GPU calculate node distributes x hash chain task；Then by residue
Y hash chain task order be reallocated in n GPU calculate node preceding y GPU calculate nodes, be preceding y GPU meters
Each GPU calculate node in operator node distributes a hash chain task；
2) each GPU calculate node concurrently generates a rainbow table according to the hash chain task of respective distribution；
If 3) GPU calculate nodes generation rainbow telogenesis work(, rainbow table generation logging unit 301 writes corresponding coloured silk
Rainbow table generation mark logflags is 1；
4) daily record inspection unit 302 checks rainbow table generation mark, if rainbow table generation mark logflags is 0,
Represent that the generation of rainbow table is unsuccessful, then file system 30 calls corresponding GPU calculate nodes to continue to generate rainbow table, if rainbow
Table generation mark logflags is 1, then it represents that rainbow table is generated successfully, and file system 30 stores the rainbow table being successfully generated.
(2) lookup of rainbow table
1) joint of the chain tail of the hash chain in the rainbow table of generation is indexed packet, the joint of the chain tail in packet is entered
Row sequence；
2) in the rainbow table of indexed packet and sequence, index search and then execution two are first carried out to ciphertext to be decrypted
Divide and search, decrypted with obtaining corresponding completion in plain text.
The 64 bit length integer values calculated during rainbow table search are right in order to be quickly found out in rainbow table
Then the last-of-chain answered, usually looked into the full sequence of last-of-chain during rainbow table search using external sort method using two points
Find correspondence last-of-chain.But rainbow table data scale is huge, the efficiency of full sequence is poor, and I/O bottlenecks are very prominent.The present invention is adopted
It is multiple groups by rainbow table index with the method that sorts afterwards is first indexed, the joint of the chain tail to the rainbow chain in each group is arranged
Sequence.When cracking, first searched in the group of index, then corresponding file is loaded into internal memory, using binary chop, improve
The speed of lookup, accelerates the speed of password cracking.
In sum, the decryption method based on big data rainbow table of embodiments of the invention can be by using multiple
Hash chain in GPU calculate node parallel generation rainbow tables greatly improves rainbow table formation speed, and by generation
Rainbow table is indexed sequence to greatly shorten the rainbow table search time of decryption phase, so as to greatly shorten decryption time.Profit
To crack the password of less than 12 in 3 days, and 99% can be ensured with the decryption method based on big data rainbow table of the invention
Success rate.Decryption method based on big data rainbow table of the invention can be to LM, MD4, NTLSHASH, MD5 or SHA1 algorithm
It is decrypted, and can be easily extended.The present invention is stored using big data Hadoop technologies, using Optimal improvements
The rainbow table based on GPU generating algorithm, the formation speed of rainbow table is improve 10 times.Built using on distributed type assemblies
Vertical good index structure, the lookup for accelerating rainbow table, completion password cracking and attack tolerant checking.It is of the invention to be counted based on big
Can be applied in power network metering automation terminal according to the decryption method and decryption device of rainbow table, greatly improve power network intelligence electricity
Can table communication reliability.Using decryption method of the invention and decryption device, password cracking is rapid, and maximum duration is no more than 3 days,
The need for disclosure satisfy that power network metering automation terminal, the communication reliability demonstration of power network intelligent electric energy meter.
Those skilled in the art considering specification and practice here after disclosure of the invention, will readily occur to it is of the invention its
Its embodiment.The application is intended to any modification of the invention, purposes or adaptations, these modifications, purposes or
Person's adaptations follow general principle of the invention and including undocumented common knowledge in the art of the invention
Or conventional techniques.Description and embodiments are considered only as exemplary, and true scope and spirit of the invention are by following
Claim is pointed out.
Claims (10)
1. a kind of decryption method based on big data rainbow table, it is characterised in that including：
Rainbow table task is distributed into n GPU calculate node, wherein, the n is the integer more than 1；
Each GPU calculate node generates a rainbow table according to the rainbow table task of distribution；
The joint of the chain tail of the hash chain in the rainbow table of generation is indexed packet, the joint of the chain tail in packet is arranged
Sequence；
In the rainbow table of indexed packet and sequence, index search is first carried out to ciphertext to be decrypted and then two points are performed and looked into
Look for, to obtain corresponding completion decryption in plain text.
2. the decryption method based on big data rainbow table according to claim 1, it is characterised in that by rainbow table task point
N GPU calculate node of dispensing includes：
The lookup success rate of span, rainbow table according to plaintext sets the size of the rainbow table task, the rainbow
Table task includes multiple hash chain tasks, and each hash chain task will generate a hash chain；
The rainbow table task is distributed into the n GPU calculate nodes according to the quantity of hash chain task.
3. the decryption method based on big data rainbow table according to claim 2, it is characterised in that in hash chain task
In the case that quantity is m, m/n=x+y, wherein, x is the business that is obtained divided by n of m, and y is remainder, and m is that integer more than 1, x are big
In 0 integer, y is integer, and the rainbow table task is distributed into the n GPU calculate nodes includes：
Each the GPU calculate node being first in the n GPU calculate nodes distributes x hash chain task；
Then the preceding y GPU remaining y hash chain task order being reallocated in the n GPU calculate nodes is calculated
Node, is that each the GPU calculate node in the preceding y GPU calculate nodes distributes a hash chain task.
4. the decryption method based on big data rainbow table according to claim 1, it is characterised in that the rainbow table that will be generated
In the joint of the chain tail of hash chain be indexed packet, the joint of the chain tail in packet is ranked up including：
The magnitude range of the binary numeral of the joint of the chain tail according to hash chain is indexed packet come the rainbow table to generation；
Joint of the chain tail to the hash chain in each packet is ranked up according to the size order of binary numeral.
5. the decryption method based on big data rainbow table according to claim 1, it is characterised in that
The ciphertext to be decrypted passes through LM, MD4, NTLSHASH, MD5 or SHA1 algorithm for encryption, with the ciphertext to be decrypted
Corresponding password is 1-12.
6. a kind of decryption device based on big data rainbow table, it is characterised in that including：
N GPU calculate node, is allocated rainbow table task, and each GPU calculate node generates a rainbow table, and n is more than 1
Integer；
Rainbow table index sequencing unit, for the chain periproct of the hash chain in the rainbow table that is generated to the n GPU calculate nodes
Point is indexed packet, and the joint of the chain tail in packet is ranked up；
Searching unit, in the rainbow table of indexed packet and sequence, first carrying out index search to ciphertext to be decrypted right
After perform binary chop, corresponding complete decryption in plain text to obtain.
7. the decryption device based on big data rainbow table according to claim 6, it is characterised in that also including file system
System, for distributing rainbow table task to the n GPU calculate nodes, stores the rainbow table of the n GPU calculate nodes generation.
8. the decryption device based on big data rainbow table according to claim 7, it is characterised in that the file system bag
Include：
Rainbow table generates logging unit, and for setting rainbow table generation data parameters for each GPU calculate node, write-in is color
Whether rainbow table generation mark, the rainbow table generation mark succeeds for indicating rainbow table to generate；
Daily record inspection unit, for checking the rainbow table generation mark, if rainbow table generation mark indicates rainbow table
Generation is unsuccessful, calls corresponding GPU calculate nodes to continue to generate rainbow table.
9. the decryption device based on big data rainbow table according to claim 7, it is characterised in that the file system is also
Including：
GPU dispensing units, for the span according to plaintext, the lookup success rate of rainbow table for each GPU calculate node sets
Put calculating parameter, data transfer and generating algorithm.
10. the decryption device based on big data rainbow table according to claim 6, it is characterised in that also including storage battle array
Row, the rainbow table for storing indexed packet and sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611147432.0A CN106712928A (en) | 2016-12-13 | 2016-12-13 | Big data rainbow table based decryption method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611147432.0A CN106712928A (en) | 2016-12-13 | 2016-12-13 | Big data rainbow table based decryption method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106712928A true CN106712928A (en) | 2017-05-24 |
Family
ID=58937362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611147432.0A Pending CN106712928A (en) | 2016-12-13 | 2016-12-13 | Big data rainbow table based decryption method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106712928A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107425957A (en) * | 2017-08-31 | 2017-12-01 | 郑州云海信息技术有限公司 | A kind of cryptographic attack method, apparatus and isomery accelerate platform |
| CN107465500A (en) * | 2017-07-20 | 2017-12-12 | 广州慧睿思通信息科技有限公司 | MD5 Brute Force system and methods based on FPGA |
| CN108038382A (en) * | 2017-10-18 | 2018-05-15 | 北京丁牛科技有限公司 | The processing method and system of rainbow chained list based on CPU-GPU frameworks |
| CN108416208A (en) * | 2018-02-05 | 2018-08-17 | 深圳大普微电子科技有限公司 | A kind of method of decryption, host equipment and storage device |
| CN109840245A (en) * | 2019-01-31 | 2019-06-04 | 中铁工程装备集团有限公司 | A kind of data query engine stored based on fragment and index by half |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103049709A (en) * | 2013-01-22 | 2013-04-17 | 上海交通大学 | Code recovery system and recovery method based on generator and extended rainbow table |
| CN103400072A (en) * | 2013-07-31 | 2013-11-20 | 厦门市美亚柏科信息股份有限公司 | Hash value password recovering method and device |
| CN103714300A (en) * | 2014-01-06 | 2014-04-09 | 武汉虹旭信息技术有限责任公司 | Encryption and analysis system based on distributed GPU and rainbow table and method of encryption and analysis system |
| CN105933120A (en) * | 2016-04-06 | 2016-09-07 | 清华大学 | Spark platform-based password hash value recovery method and device |
-
2016
- 2016-12-13 CN CN201611147432.0A patent/CN106712928A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103049709A (en) * | 2013-01-22 | 2013-04-17 | 上海交通大学 | Code recovery system and recovery method based on generator and extended rainbow table |
| CN103400072A (en) * | 2013-07-31 | 2013-11-20 | 厦门市美亚柏科信息股份有限公司 | Hash value password recovering method and device |
| CN103714300A (en) * | 2014-01-06 | 2014-04-09 | 武汉虹旭信息技术有限责任公司 | Encryption and analysis system based on distributed GPU and rainbow table and method of encryption and analysis system |
| CN105933120A (en) * | 2016-04-06 | 2016-09-07 | 清华大学 | Spark platform-based password hash value recovery method and device |
Non-Patent Citations (2)
| Title |
|---|
| 马思硕: "《基于GPU的彩虹表弱口令旁路检查工具》", 《电气应用增刊》 * |
| 黄东江: "《GPU集群上彩虹表构造与查找的研究与实现》", 《中国优秀硕士学位论文全文数据库（电子期刊）》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107465500A (en) * | 2017-07-20 | 2017-12-12 | 广州慧睿思通信息科技有限公司 | MD5 Brute Force system and methods based on FPGA |
| CN107465500B (en) * | 2017-07-20 | 2020-04-03 | 广州慧睿思通信息科技有限公司 | MD5 brute force cracking system and method based on FPGA |
| CN107425957A (en) * | 2017-08-31 | 2017-12-01 | 郑州云海信息技术有限公司 | A kind of cryptographic attack method, apparatus and isomery accelerate platform |
| CN107425957B (en) * | 2017-08-31 | 2021-02-19 | 苏州浪潮智能科技有限公司 | Password attack method and device and heterogeneous acceleration platform |
| CN108038382A (en) * | 2017-10-18 | 2018-05-15 | 北京丁牛科技有限公司 | The processing method and system of rainbow chained list based on CPU-GPU frameworks |
| CN108416208A (en) * | 2018-02-05 | 2018-08-17 | 深圳大普微电子科技有限公司 | A kind of method of decryption, host equipment and storage device |
| CN109840245A (en) * | 2019-01-31 | 2019-06-04 | 中铁工程装备集团有限公司 | A kind of data query engine stored based on fragment and index by half |
| CN109840245B (en) * | 2019-01-31 | 2020-12-18 | 中铁工程装备集团有限公司 | Data query engine based on fragment storage and half-folded index |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106712928A (en) | Big data rainbow table based decryption method and device | |
| CN103546288B (en) | SM2 (streaming multiprocessor 2) digital signature generating algorithm realizing method and device | |
| CN108063758A (en) | For the node in the signature verification method of block chain network and block chain network | |
| CN104615945A (en) | Code cracking method and system based on multiple GPU cracking devices | |
| CN103995827B (en) | High-performance sort method in MapReduce Computational frames | |
| CN112217642A (en) | Data encryption sharing method and device, electronic equipment and computer storage medium | |
| CN115795517A (en) | Asset data storage method and device | |
| US11250004B2 (en) | Secure equijoin system, secure equijoin device, secure equijoin method, and program | |
| CN111950032A (en) | Block chain-based data storage method, terminal device and storage medium | |
| CN112182109A (en) | Distributed data coding storage method based on block chain and electronic equipment | |
| CN111898135A (en) | Data processing method, data processing apparatus, computer device, and medium | |
| Lu et al. | GSNP: a DNA single-nucleotide polymorphism detection system with GPU acceleration | |
| JPWO2019208485A1 (en) | Secret Aggregation Maximum Value System, Secret Aggregation Minimum Value System, Secret Computing Unit, Secret Aggregation Maximum Value Method, Secret Aggregation Minimum Value Method, and Program | |
| CN112783989A (en) | Data processing method and device based on block chain | |
| CN111951112A (en) | Intelligent contract execution method based on block chain, terminal equipment and storage medium | |
| CN112182108A (en) | Block chain based distributed data storage updating method and electronic equipment | |
| US10333697B2 (en) | Nondecreasing sequence determining device, method and program | |
| CN107122849B (en) | Spark R-based product detection total completion time minimization method | |
| CN112217639B (en) | Data encryption sharing method and device, electronic equipment and computer storage medium | |
| CN110135178A (en) | Zero-lag account book access technique in the verifying of block chain | |
| CN115643090A (en) | Longitudinal federal analysis method, device, equipment and medium based on privacy retrieval | |
| CN113918517A (en) | Multi-type file centralized management method, device, equipment and storage medium | |
| Chopard et al. | Problems, algorithms, and computational complexity | |
| Yang et al. | cuxcmp: Cuda-accelerated private comparison based on homomorphic encryption | |
| CN112181308A (en) | Block chain based distributed data storage method and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170524 |