Intelligent contract vulnerability detection method based on multi-task learning
The invention discloses an intelligent contract vulnerability detection method based on multi-task learning. An intelligent contract vulnerability detection technology is realized by using a multi-task learning framework based on hard parameter sharing. Firstly, in a data preparation stage, an intel...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | KINBI DING JINFEI BU KUIJIAN ZHOU KUO WANG MENGXIAO HAN HONGGUI LI DONGMENG WANG XI HUANG JING |
| description | The invention discloses an intelligent contract vulnerability detection method based on multi-task learning. An intelligent contract vulnerability detection technology is realized by using a multi-task learning framework based on hard parameter sharing. Firstly, in a data preparation stage, an intelligent contract data set is cleaned, and vulnerability classification and label marking are performed through an existing detection tool; in the data preprocessing stage, an intelligent contract sample source code is compiled to form a byte code, then the byte code is cleaned, then decompiled and converted into an operation code sequence, and input of a model is formed; then, in a model construction stage, constructing an intelligent contract detection model based on multi-task learning; and finally, in a training stage, according to the operation code sequence obtained in the data preprocessing stage, inputting the operation code sequence into the model for training so as to realize judgment and detection of vulne |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114218580A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114218580A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114218580A3</originalsourceid><addsrcrecordid>eNqNyj0KwkAQhuE0FqLeYTxAwPgDaSUo2oiFfZhsvsTFcTbsTgRvL4IHsHp54J1m17MaRHwPNXJBLbIzeo2iiNx48famFgZnPig9YffQUsMJLX09ivncOD1IwFG99vNs0rEkLH6dZcvj4VadcgyhRhrYQWF1dSmK7bood-Vqv_nn-QAKHzgR</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Intelligent contract vulnerability detection method based on multi-task learning</title><source>esp@cenet</source><creator>KINBI ; DING JINFEI ; BU KUIJIAN ; ZHOU KUO ; WANG MENGXIAO ; HAN HONGGUI ; LI DONGMENG ; WANG XI ; HUANG JING</creator><creatorcontrib>KINBI ; DING JINFEI ; BU KUIJIAN ; ZHOU KUO ; WANG MENGXIAO ; HAN HONGGUI ; LI DONGMENG ; WANG XI ; HUANG JING</creatorcontrib><description>The invention discloses an intelligent contract vulnerability detection method based on multi-task learning. An intelligent contract vulnerability detection technology is realized by using a multi-task learning framework based on hard parameter sharing. Firstly, in a data preparation stage, an intelligent contract data set is cleaned, and vulnerability classification and label marking are performed through an existing detection tool; in the data preprocessing stage, an intelligent contract sample source code is compiled to form a byte code, then the byte code is cleaned, then decompiled and converted into an operation code sequence, and input of a model is formed; then, in a model construction stage, constructing an intelligent contract detection model based on multi-task learning; and finally, in a training stage, according to the operation code sequence obtained in the data preprocessing stage, inputting the operation code sequence into the model for training so as to realize judgment and detection of vulne</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2022</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220322&DB=EPODOC&CC=CN&NR=114218580A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76418</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220322&DB=EPODOC&CC=CN&NR=114218580A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KINBI</creatorcontrib><creatorcontrib>DING JINFEI</creatorcontrib><creatorcontrib>BU KUIJIAN</creatorcontrib><creatorcontrib>ZHOU KUO</creatorcontrib><creatorcontrib>WANG MENGXIAO</creatorcontrib><creatorcontrib>HAN HONGGUI</creatorcontrib><creatorcontrib>LI DONGMENG</creatorcontrib><creatorcontrib>WANG XI</creatorcontrib><creatorcontrib>HUANG JING</creatorcontrib><title>Intelligent contract vulnerability detection method based on multi-task learning</title><description>The invention discloses an intelligent contract vulnerability detection method based on multi-task learning. An intelligent contract vulnerability detection technology is realized by using a multi-task learning framework based on hard parameter sharing. Firstly, in a data preparation stage, an intelligent contract data set is cleaned, and vulnerability classification and label marking are performed through an existing detection tool; in the data preprocessing stage, an intelligent contract sample source code is compiled to form a byte code, then the byte code is cleaned, then decompiled and converted into an operation code sequence, and input of a model is formed; then, in a model construction stage, constructing an intelligent contract detection model based on multi-task learning; and finally, in a training stage, according to the operation code sequence obtained in the data preprocessing stage, inputting the operation code sequence into the model for training so as to realize judgment and detection of vulne</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyj0KwkAQhuE0FqLeYTxAwPgDaSUo2oiFfZhsvsTFcTbsTgRvL4IHsHp54J1m17MaRHwPNXJBLbIzeo2iiNx48famFgZnPig9YffQUsMJLX09ivncOD1IwFG99vNs0rEkLH6dZcvj4VadcgyhRhrYQWF1dSmK7bood-Vqv_nn-QAKHzgR</recordid><startdate>20220322</startdate><enddate>20220322</enddate><creator>KINBI</creator><creator>DING JINFEI</creator><creator>BU KUIJIAN</creator><creator>ZHOU KUO</creator><creator>WANG MENGXIAO</creator><creator>HAN HONGGUI</creator><creator>LI DONGMENG</creator><creator>WANG XI</creator><creator>HUANG JING</creator><scope>EVB</scope></search><sort><creationdate>20220322</creationdate><title>Intelligent contract vulnerability detection method based on multi-task learning</title><author>KINBI ; DING JINFEI ; BU KUIJIAN ; ZHOU KUO ; WANG MENGXIAO ; HAN HONGGUI ; LI DONGMENG ; WANG XI ; HUANG JING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114218580A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>KINBI</creatorcontrib><creatorcontrib>DING JINFEI</creatorcontrib><creatorcontrib>BU KUIJIAN</creatorcontrib><creatorcontrib>ZHOU KUO</creatorcontrib><creatorcontrib>WANG MENGXIAO</creatorcontrib><creatorcontrib>HAN HONGGUI</creatorcontrib><creatorcontrib>LI DONGMENG</creatorcontrib><creatorcontrib>WANG XI</creatorcontrib><creatorcontrib>HUANG JING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KINBI</au><au>DING JINFEI</au><au>BU KUIJIAN</au><au>ZHOU KUO</au><au>WANG MENGXIAO</au><au>HAN HONGGUI</au><au>LI DONGMENG</au><au>WANG XI</au><au>HUANG JING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Intelligent contract vulnerability detection method based on multi-task learning</title><date>2022-03-22</date><risdate>2022</risdate><abstract>The invention discloses an intelligent contract vulnerability detection method based on multi-task learning. An intelligent contract vulnerability detection technology is realized by using a multi-task learning framework based on hard parameter sharing. Firstly, in a data preparation stage, an intelligent contract data set is cleaned, and vulnerability classification and label marking are performed through an existing detection tool; in the data preprocessing stage, an intelligent contract sample source code is compiled to form a byte code, then the byte code is cleaned, then decompiled and converted into an operation code sequence, and input of a model is formed; then, in a model construction stage, constructing an intelligent contract detection model based on multi-task learning; and finally, in a training stage, according to the operation code sequence obtained in the data preprocessing stage, inputting the operation code sequence into the model for training so as to realize judgment and detection of vulne</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN114218580A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Intelligent contract vulnerability detection method based on multi-task learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T21%3A59%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=KINBI&rft.date=2022-03-22&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114218580A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |