US 11,683,335 B2
Artificial intelligence vendor similarity collation
Ghada I. Khashab, Allen, TX (US); Lori Mammoser, Charlotte, NC (US); Anthony R. Bandos, Clarkston, MI (US); Peggy J. Qualls, Oswego, IL (US); Sidy Diop, Charlotte, NC (US); and Ajay Jose Paul, Davidson, NC (US)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Jan. 15, 2021, as Appl. No. 17/149,846.
Prior Publication US 2022/0232030 A1, Jul. 21, 2022
Int. Cl. H04L 29/00 (2006.01); H04L 9/40 (2022.01); G06N 20/00 (2019.01)
CPC H04L 63/1433 (2013.01) [G06N 20/00 (2019.01); H04L 63/20 (2013.01)] 7 Claims
OG exemplary drawing
 
1. An artificial intelligence (“AI”) method for unifying cybersecurity vulnerabilities detected by disparate software tools deployed across an enterprise organization, the AI method comprising:
detecting a first vendor tool operating on a target hardware system;
in response to detecting the first vendor tool, connecting an AI engine to a first application program interface (“API”) that outputs a first cyberthreat formulated by the first vendor tool;
detecting a second vendor tool operating on the target hardware system;
in response to detecting the second vendor tool, connecting the AI engine to a second API that outputs a second cyberthreat formulated by the second vendor tool;
applying machine learning techniques to the first cyberthreat and the second cyberthreat and thereby determining that the first cyberthreat and the second cyberthreat correspond to a known cyberthreat;
prioritizing allocation of computing resources to neutralize the known cyberthreat;
wherein:
the first vendor tool includes a first set of cyberthreats that include a threshold number of known cyberthreats associated with the target hardware system;
the second vendor tool includes a second set of cyberthreats that includes the threshold number of known cyberthreats; and
in response to detecting the threshold number of known cyberthreats, registering the first and second vendor tools as generating duplicative outputs for the target hardware system.