Changeflow GovPing Telecom & Technology USPTO Patent US12585772B2: Malicious Activity D...
Routine Notice Added Final

USPTO Patent US12585772B2: Malicious Activity Detection

Favicon for changeflow.com ChangeBridge: Patent Grants - AI & Computing (G06N)
Published March 24th, 2026
Detected March 25th, 2026
Email

Summary

The USPTO has granted patent US12585772B2 to Acronis International GmbH for a method of detecting malicious activity on endpoints. The patent describes using machine learning models trained on sequences of process behavior events to identify and alert on potential threats.

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12585772B2, titled 'Malicious activity detection by modeling end-point events as sequences,' to Acronis International GmbH. The patent details a system and method for detecting malicious activity on an endpoint by tracking process behavior, generating a provenance graph, transforming it into a sequence of events, and training a machine learning model to classify sequences and generate a probability of maliciousness. This patent covers novel approaches to endpoint security through advanced behavioral analysis and machine learning.

This patent grant represents a new intellectual property asset in the field of cybersecurity. While not a regulatory requirement, it signifies innovation in threat detection technologies. Companies developing or utilizing endpoint security solutions, particularly those employing machine learning for behavioral analysis, should be aware of this patent. No immediate compliance actions are required for regulated entities, but it may influence future technology development and licensing considerations in the cybersecurity sector.

Source document (simplified)

← USPTO Patent Grants

Malicious activity detection by modeling end-point events as sequences

Grant US12585772B2 Kind: B2 Mar 24, 2026

Assignee

Acronis International GmbH

Inventors

Candid Wuest, Philipp Gysel, Dinil Mon Divakaran, Andrey Ustyuzhanin, Kenneth Nwafor, Serg Bell, Stanislav Protasov

Abstract

Systems and methods for detecting malicious activity on an endpoint, the endpoint having executing processes, including tracking behavior of executing processes, generating a provenance graph to group the behavior events, transforming the provenance graph into a sequence of behavior events, training a sequence classification machine learning model based on the sequence of behavior events, processing a sequence of test behavior events using the sequence classification machine learning model to generate a probability of maliciousness, and alerting for malicious activity when the probability of maliciousness for the sequence of test behavior events is greater than a threshold.

CPC Classifications

G06N 3/047 G06N 20/00 G06F 21/566 G06F 2221/034

Filing Date

2023-09-19

Application No.

18470237

Claims

20

View original document →

Named provisions

Malicious activity detection by modeling end-point events as sequences

Classification

Agency
USPTO
Published
March 24th, 2026
Instrument
Notice
Legal weight
Non-binding
Stage
Final
Change scope
Minor
Document ID
US12585772B2

Who this affects

Applies to
Technology companies
Industry sector
5112 Software & Technology 3341 Computer & Electronics Manufacturing
Activity scope
Malicious Activity Detection Endpoint Security
Geographic scope
United States US

Taxonomy

Primary area
Cybersecurity
Operational domain
IT Security
Topics
Artificial Intelligence Data Privacy

Get Telecom & Technology alerts

Weekly digest. AI-summarized, no noise.

Free. Unsubscribe anytime.

Get alerts for this source

We'll email you when ChangeBridge: Patent Grants - AI & Computing (G06N) publishes new changes.

Free. Unsubscribe anytime.