IP Library Granted Patent US 12,373,567
Granted Patent B2
US 12,373,567 · App. 17/821,914 · Granted Jul 29, 2025

Techniques for detecting exploitation of manufacturing device vulnerabilities

Inventors: Shaked Gitelman (Tel Aviv, IL); Tal Ravid (Tel Aviv, IL)
G06F21/577G06F21/554G06N5/04G06N20/00G06F2221/034
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,373,567
App. No.
17/821,914
Granted
Jul 29, 2025
Kind
B2
Abstract

A system and method for determining device attributes using a classifier hierarchy. The method includes determining exploitation conditions for a manufacturing device based on a first set of device attributes of the manufacturing device and a second set of device attributes indicated in a vulnerabilities database; analyzing behavior and configuration of the manufacturing device to detect an exploitable vulnerability for the manufacturing device, wherein the exploitable vulnerability is a behavior or configuration of the manufacturing device which meets the exploitation conditions; and performing mitigation actions based on the exploitable vulnerability. The vulnerabilities database further indicates known exploits for the second set of device attributes. Analyzing the behavior and configuration of the manufacturing device includes identifying that a port is open and querying a vulnerability scanner for identifying information of the open port, wherein the currently exploitable vulnerability is detected based further on the identifying information of the open port.

Claims (44)

1. A method for detecting manufacturing device exploitable vulnerabilities, comprising:

sequentially applying a plurality of sub-models of a hierarchy to a plurality of features extracted from device activity data, wherein each sub-model outputs a class when applied to at least a portion of the plurality of features, wherein each class comprises a classifier output representing a device attribute, wherein applying the plurality of sub-models further comprises iteratively determining a next sub-model to apply based on the classifier output by a most recently applied sub-model and the hierarchy;

determining a first device attribute of a manufacturing device based on the classifier output by a last sub-model of the sequentially applied plurality of sub-models;

determining at least one exploitation condition for the manufacturing device based on the first device attribute of the manufacturing device and a plurality of second device attributes indicated in a vulnerabilities database, wherein the vulnerabilities database further indicates a plurality of known exploits for the plurality of second device attributes;

analyzing the manufacturing device to detect an exploitable vulnerability for the manufacturing device, wherein the exploitable vulnerability is a behavior or configuration of the manufacturing device which meets the at least one exploitation condition, wherein analyzing the behavior and configuration of the manufacturing device further comprises identifying that a port is open and querying a vulnerability scanner for identifying information of the open port; and

performing at least one mitigation action based on the exploitable vulnerability.

2. The method of claim 1 , wherein the first device attribute includes a device type, wherein the behavior of the manufacturing device includes communicating with another device, wherein the plurality of known exploits includes communicating with an unapproved type of device.

3. The method of claim 2 , wherein the other device is an unapproved type of device, wherein performing the at least one mitigation action further comprises:

severing a connection between the manufacturing device and the other device.

4. The method of claim 1 , wherein the first device attribute includes a device type, wherein the behavior of the manufacturing device includes receiving update data from another device, wherein the plurality of known exploits includes receiving update data from an unapproved type of device.

5. The method of claim 4 , wherein the other device is an unapproved type of device, wherein performing the at least one mitigation action further comprises:

deleting the update data received from the other device; and

sending new update data to the manufacturing device.

6. The method of claim 1 , wherein the manufacturing device is any of a programmable logic controller, a human-machine interface, a supervisory control and data acquisition (SCADA) system, an engineering station, and a historian server.

7. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process, the process comprising:

sequentially applying a plurality of sub-models of a hierarchy to a plurality of features extracted from device activity data, wherein each sub-model outputs a class when applied to at least a portion of the plurality of features, wherein each class comprises a classifier output representing a device attribute, wherein applying the plurality of sub-models further comprises iteratively determining a next sub-model to apply based on the classifier output by a most recently applied sub-model and the hierarchy;

determining a first device attribute of a manufacturing device based on the classifier output by a last sub-model of the sequentially applied plurality of sub-models;

determining at least one exploitation condition for a manufacturing device based on the first device attribute of the manufacturing device and a plurality of second device attributes indicated in a vulnerabilities database, wherein the vulnerabilities database further indicates a plurality of known exploits for the plurality of second device attributes;

analyzing manufacturing device to detect an exploitable vulnerability for the manufacturing device, wherein the exploitable vulnerability is a behavior or configuration of the manufacturing device which meets the at least one exploitation condition, wherein analyzing the behavior and configuration of the manufacturing device further comprises identifying that a port is open and querying a vulnerability scanner for identifying information of the open port; and

performing at least one mitigation action based on the exploitable vulnerability.

8. A system for determining device attributes using a classifier hierarchy, comprising:

a processing circuitry; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

sequentially applying a plurality of sub-models of a hierarchy to a plurality of features extracted from device activity data, wherein each sub-model outputs a class when applied to at least a portion of the plurality of features, wherein each class comprises a classifier output representing a device attribute, wherein applying the plurality of sub-models further comprises iteratively determining a next sub-model to apply based on the classifier output by a most recently applied sub-model and the hierarchy;

determining a first device attribute of a manufacturing device based on the classifier output by a last sub-model of the sequentially applied plurality of sub-models;

determine at least one exploitation condition for the manufacturing device based on a first device attribute of the manufacturing device and a plurality of second device attributes indicated in a vulnerabilities database, wherein the vulnerabilities database further indicates a plurality of known exploits for the plurality of second device attributes;

analyze the manufacturing device to detect an exploitable vulnerability for the manufacturing device, wherein the exploitable vulnerability is a behavior or configuration of the manufacturing device which meets the at least one exploitation condition, wherein analyzing the behavior and configuration of the manufacturing device further includes identifying that a port is open and querying a vulnerability scanner for identifying information of the open port; and

perform at least one mitigation action based on the exploitable vulnerability.

9. The system of claim 8 , wherein the first device attribute includes a device type, wherein the behavior of the manufacturing device includes communicating with another device, wherein the plurality of known exploits includes communicating with an unapproved type of device.

10. The system of claim 9 , wherein the other device is an unapproved type of device, wherein the system is further configured to:

sever a connection between the manufacturing device and the other device.

11. The system of claim 8 , wherein the first device attribute includes a device type, wherein the behavior of the manufacturing device includes receiving update data from another device, wherein the plurality of known exploits includes receiving update data from an unapproved type of device.

12. The system of claim 11 , wherein the other device is an unapproved type of device, wherein the system is further configured to:

delete the update data received from the other device; and

send new update data to the manufacturing device.

13. The system of claim 8 , wherein the manufacturing device is any of a programmable logic controller, a human-machine interface, a supervisory control and data acquisition (SCADA) system, an engineering station, and a historian server.

14. The non-transitory computer readable medium of claim 7 , wherein the first device attribute includes a device type, wherein the behavior of the manufacturing device includes communicating with another device, wherein the plurality of known exploits includes communicating with an unapproved type of device.

15. The non-transitory computer readable medium of claim 14 , wherein the other device is an unapproved type of device, wherein the system is further configured to:

sever a connection between the manufacturing device and the other device.

16. The non-transitory computer readable medium of claim 7 , wherein the first device attribute includes a device type, wherein the behavior of the manufacturing device includes receiving update data from another device, wherein the plurality of known exploits includes receiving update data from an unapproved type of device.

17. The non-transitory computer readable medium of claim 7 , wherein the other device is an unapproved type of device, wherein the system is further configured to:

delete the update data received from the other device; and

send new update data to the manufacturing device.

18. The non-transitory computer readable medium of claim 7 , wherein the manufacturing device is any of a programmable logic controller, a human-machine interface, a supervisory control and data acquisition (SCADA) system, an engineering station, and a historian server.

Assignments (3)
RELEASE OF SECURITY INTEREST Recorded Apr 21, 2026
From: HERCULES CAPITAL, INC.
To: ARMIS SECURITY LTD; ARMIS INC.
Reel/Frame 075477/0965 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 17, 2025
From: GITELMAN, SHAKED; RAVID, TAL
To: ARMIS SECURITY LTD.
Reel/Frame 071441/0123 →
INTELLECTUAL PROPERTY SECURITY AGREEMENT Recorded Mar 5, 2024
From: ARMIS SECURITY LTD.
To: HERCULES CAPITAL, INC., AS ADMINISTRATIVE AND COLLATERAL AGENT
Reel/Frame 066740/0499 →
Continuity (2)
Continuation 16801748 · Feb 26, 2020
Related Publication 20220414230A1 · Dec 29, 2022
References Cited (64)
US 9749349B1 · Czarny · 2017 [cited by applicant]
US 11277426B1 · Kazemeyni · 2022 [cited by examiner]
US 11481503B2 · Gitelman et al. · 2022 [cited by applicant]
US 20050160480A1 · Birt · 2005 [cited by applicant]
US 20080289027A1 · Yariv et al. · 2008 [cited by applicant]
US 20110251960A1 · Holla et al. · 2011 [cited by applicant]
US 20130247194A1 · Jha et al. · 2013 [cited by applicant]
US 20150346066A1 · Dutta · 2015 [cited by applicant]
US 20150379371A1 · Yoon · 2015 [cited by applicant]
US 20160094578A1 · McQuillan et al. · 2016 [cited by applicant]
US 20170090499A1 · Dolan · 2017 [cited by applicant]
US 20170250855A1 · Patil · 2017 [cited by applicant]
US 20180124096A1 · Schwartz · 2018 [cited by applicant]
US 20180191593A1 · DeKnijf · 2018 [cited by applicant]
US 20180225592A1 · Ponnuswamy · 2018 [cited by applicant]
US 20180332069A1 · Moore et al. · 2018 [cited by applicant]
US 20180351987A1 · Patel et al. · 2018 [cited by applicant]
US 20180359278A1 · Rusakov · 2018 [cited by applicant]
US 20190020641A1 · Wasily et al. · 2019 [cited by applicant]
US 20190095587A1 · Warner et al. · 2019 [cited by applicant]
US 20190215688A1 · Zavesky et al. · 2019 [cited by applicant]
US 20190238584A1 · Somasundaram et al. · 2019 [cited by applicant]
US 20190258807A1 · DiMaggio · 2019 [cited by applicant]
US 20190294485A1 · Kukreja · 2019 [cited by applicant]
US 20190318100A1 · Bhatia · 2019 [cited by applicant]
US 20190362076A1 · Wang et al. · 2019 [cited by applicant]
US 20190392152A1 · Patel et al. · 2019 [cited by applicant]
US 20200051697A1 · Krishnamurti et al. · 2020 [cited by applicant]
US 20200076853A1 · Pandian · 2020 [cited by applicant]
US 20200097651A1 · Mestha et al. · 2020 [cited by applicant]
US 20200143061A1 · Kim · 2020 [cited by applicant]
US 20200201620A1 · Beard · 2020 [cited by applicant]
US 20200210592A1 · Karas et al. · 2020 [cited by applicant]
US 20200210871A1 · Alperovich et al. · 2020 [cited by applicant]
US 20200222010A1 · Howard · 2020 [cited by applicant]
US 20200244677A1 · Abbaszadeh · 2020 [cited by applicant]
US 20200403991A1 · Sohail et al. · 2020 [cited by applicant]
US 20210029153A1 · Sugimoto · 2021 [cited by applicant]
US 20210056404A1 · Goswami · 2021 [cited by applicant]
US 20210073658A1 · Poole · 2021 [cited by applicant]
US 20210232291A1 · Abdulaal · 2021 [cited by applicant]
US 20210264035A1 · Gitelman et al. · 2021 [cited by applicant]
CN 112019494A · 2020 [cited by applicant]
CN 114255830A · 2022 [cited by applicant]
EP 3745291A1 · 2020 [cited by applicant]
WO 2018071845A1 · 2018 [cited by applicant]
WO 2020093020A1 · 2020 [cited by applicant]
WO 2020141486A1 · 2020 [cited by applicant]
WO 2021105995A1 · 2021 [cited by applicant]
U.S. Appl. No. 16/801,681, filed Feb. 26, 2020, Shaked Gitelman. [cited by applicant]
Alsuwaidi et al., “Security Vulnerabilities Detected in Medical Devices”, 12th Annual Undergraduate Research Conference on Applied Computing (URC2020), United Arab Emirates University, College of IT, Department of Infor… [cited by applicant]
Beavers et al., “Recent Cyber Attacks and Vulnerabilities in Medical Devices and Healthcare Institutions”, Part of the Advanced Sciences and Technologies for Security Applications book series (ASTSA), 2019. [cited by applicant]
International Search Report and Written Opinion of International Searching Authority for PCT/IB2021/050432, ISA/RU, Jerusalem, IL Dated: Apr. 22, 2021. [cited by applicant]
International Search Report and Written Opinion of International Searching Authority for PCT/IB2021/050433, ISA/IL, Jerusalem, Israel, Dated: Apr. 25, 2021. [cited by applicant]
Mcmahon et al., “Assessing Medical Device Vulnerabilities on the Internet of Things”, Department of Management Information Systems: The University of Arizona, 2017, pp. 176-178. [cited by applicant]
Williams et al., “Cybersecurity vulnerabilities in medical devices: a complex environment and multifaceted problem”, 2015, eHealth Research Group and Security Research Institute, Edith Cowan University, Perth, WA, Austr… [cited by applicant]
Wood et al., “Cleartext Data Transmissions in Consumer IoT Medical Devices” IoT S&P'17, Nov. 3, 2017. [cited by applicant]
Stine, “A cyber risk scoring system for medical devices,” International Journal of Critical Infrastructure Protection, Dec. 2017, vol. 19, pp. 32-46. [cited by applicant]
Pandian, “Security Challenges of IoT and Medical Devices in Healthcare,” Internet of Things, 1st Edition, 2020, Chapter 6, pp. 87-106. [cited by applicant]
Mahler, “A New Methodology for Information Security Risk Assessment for Medical Devices and Its Evaluation,” 2020, The Department of Software and Information Systems Engineering, Ben-Gurion University of the Negev, Isra… [cited by applicant]
Zaldivar, “Investigating the Security Threats on Networked Medical Devices,” 2020, 10th Annual Computing and Communication Workshop and Conference, Jan. 2020. [cited by applicant]
Ang Cui et al., “When Firmware Modifications Attack: A Case Study of Embedded Exploitation”, Jan. 1, 2013, XP055711221, DOI: 10.7916/D8P55NKB, Retrieved from the Internet: URL:https://web.archive.org/web/20150926051553i… [cited by applicant]
Anonymous: “Recovery”, Nov. 20, 2019, pp. 1-16, XP093108397, Retrieved from the Internet on Dec. 4, 2024: URL:https://web.archive.org/web/20191120050356/https://hack-technicolor.readthedocs.io/en/stable/Recovery/. [cited by applicant]
Extended European Search Report from the European Patent Office (EPO) on corresponding EP Application No. EP21760709.2 dated Dec. 12, 2023, 8 pages. [cited by applicant]
Cited By (3)
US 12,572,846 US 12,574,399 US 12,695,752