Identification of mislabeled samples via phantom nodes in label propagation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F19%3A00476515" target="_blank" >RIV/67985807:_____/19:00476515 - isvavai.cz</a>
Result on the web
<a href="http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=1&f=G&l=50&co1=AND&d=PTXT&s1=10198576.PN.&OS=PN/10198576&RS=PN/10198576" target="_blank" >http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=1&f=G&l=50&co1=AND&d=PTXT&s1=10198576.PN.&OS=PN/10198576&RS=PN/10198576</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Identification of mislabeled samples via phantom nodes in label propagation
Original language description
Systems and method identify potentially mislabeled file samples. A graph is created from a plurality of sample files. The graph includes nodes associated with the sample files and behavior nodes associated with behavior signatures. Phantom nodes are created in the graph for those sample files having a known label. During a label propagation operation, a node receives data indicating a label distribution of a neighbor node in the graph. In response to determining that the current label for the node is known, a neighborhood opinion is determined for the associated phantom node, based at least in part on the label distribution of the neighboring nodes. After the label propagation operation has completed, differences between the neighborhood opinion and the current label distribution for nodes are determined. If the difference exceeds a threshold, then the current label may be incorrect.
Czech name
—
Czech description
—
Classification
Type
P - Patent
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Patent/design ID
US10198576
Publisher
US001 -
Publisher name
United States Patent and Trademark Office (USPTO)
Place of publication
Alexandria
Publication country
US - UNITED STATES
Date of acceptance
Feb 5, 2019
Owner name
Avast Software, s. r. o. - Ústav informatiky AV ČR, v. v. i.
Method of use
A - Výsledek využívá pouze poskytovatel
Usage type
A - K využití výsledku jiným subjektem je vždy nutné nabytí licence