GENERATING HIGH-QUALITY THREAT INTELLIGENCE FROM AGGREGATED THREAT REPORTS

Mohamed Nabeel; Saravanan Thirumuruganathan; Euijin Choo; Issa M Khalil; Ting Yu

GENERATING HIGH-QUALITY THREAT INTELLIGENCE FROM AGGREGATED THREAT REPORTS

Mohamed Nabeel (Inventor), Saravanan Thirumuruganathan (Inventor), Euijin Choo (Inventor), Issa M Khalil (Inventor), Ting Yu (Inventor)

Qatar Computing Research Institute

Qatar Foundation for Education, Science, and Community Development

Research output: Patent

Abstract

Generating high-quality threat intelligence from aggregated threat reports is provided via developing a generative model that identifies relationships between a plurality of threat assessment scanners; pre-training a plurality of individual encoders based on a corresponding plurality of pretext tasks and the generative model; combining the individual encoders into a pre-trained encoder; fine-tuning the pre-trained encoder using threat data; and marking a candidate threat, as evaluated via the pre-trained encoder as fine-tuned, as one of benign or malicious.

Original language	English
Patent number	US2023205884
IPC	G06F 21/ 56 A I
Priority date	22/12/22
Publication status	Published - 29 Jun 2023

Cite this

@misc{41db58d718e74a83bddd3f29c2528d1c,

title = "GENERATING HIGH-QUALITY THREAT INTELLIGENCE FROM AGGREGATED THREAT REPORTS",

abstract = "Generating high-quality threat intelligence from aggregated threat reports is provided via developing a generative model that identifies relationships between a plurality of threat assessment scanners; pre-training a plurality of individual encoders based on a corresponding plurality of pretext tasks and the generative model; combining the individual encoders into a pre-trained encoder; fine-tuning the pre-trained encoder using threat data; and marking a candidate threat, as evaluated via the pre-trained encoder as fine-tuned, as one of benign or malicious.",

author = "Mohamed Nabeel and Saravanan Thirumuruganathan and Euijin Choo and Khalil, {Issa M} and Ting Yu",

year = "2023",

month = jun,

day = "29",

language = "English",

type = "Patent",

note = "US2023205884; G06F 21/ 56 A I",

}

TY - PAT

T1 - GENERATING HIGH-QUALITY THREAT INTELLIGENCE FROM AGGREGATED THREAT REPORTS

AU - Nabeel, Mohamed

AU - Thirumuruganathan, Saravanan

AU - Choo, Euijin

AU - Khalil, Issa M

AU - Yu, Ting

PY - 2023/6/29

Y1 - 2023/6/29

N2 - Generating high-quality threat intelligence from aggregated threat reports is provided via developing a generative model that identifies relationships between a plurality of threat assessment scanners; pre-training a plurality of individual encoders based on a corresponding plurality of pretext tasks and the generative model; combining the individual encoders into a pre-trained encoder; fine-tuning the pre-trained encoder using threat data; and marking a candidate threat, as evaluated via the pre-trained encoder as fine-tuned, as one of benign or malicious.

AB - Generating high-quality threat intelligence from aggregated threat reports is provided via developing a generative model that identifies relationships between a plurality of threat assessment scanners; pre-training a plurality of individual encoders based on a corresponding plurality of pretext tasks and the generative model; combining the individual encoders into a pre-trained encoder; fine-tuning the pre-trained encoder using threat data; and marking a candidate threat, as evaluated via the pre-trained encoder as fine-tuned, as one of benign or malicious.

M3 - Patent

M1 - US2023205884

ER -

GENERATING HIGH-QUALITY THREAT INTELLIGENCE FROM AGGREGATED THREAT REPORTS

Abstract

Fingerprint

Cite this