IP Library Granted Patent US 12,556,804
Granted Patent B2
US 12,556,804 · App. 18/419,211 · Granted Feb 17, 2026

Policy for preventing unauthorized photo capture

Inventors: Jeremy R. Fox (Georgetown, TX); Martin G. Keen (Cary, NC); Kevin W. Brew (Niskayuna, NY); Alexander Reznicek (Troy, NY)
Assignee: International Business Machines Corporation
H04N23/632G06F21/604
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 12,556,804
App. No.
18/419,211
Granted
Feb 17, 2026
Kind
B2
Abstract

A computer-implemented method (CIM), according to one embodiment, includes enacting a first policy. Enacting the first policy includes collecting location data and camera data for a first user device. Enacting the first policy further includes causing a predetermined machine learning model to use the data to determine whether the first user device is authorized to perform an image capture at a current location of the first user device. In response to a determination that an output of the predetermined machine learning model indicates that the first user device is not authorized to perform the image capture at the current location, the first user device is restricted from performing the image capture. In response to a determination that the output of the predetermined machine learning model indicates that the first user device is authorized to perform the image capture, the first user device is allowed to perform the image capture.

Claims (40)

1 . A computer-implemented method (CIM), the CIM comprising:

enacting a first policy for preventing unauthorized photo capture in sensitive areas, wherein enacting the first policy includes:

collecting location data and camera data for a first user device, wherein the first user device is associated with a user profile of a first user;

causing a predetermined machine learning model to use the location data and the camera data to determine whether the first user device is authorized to perform an image capture at a current location of the first user device;

in response to a determination that an output of the predetermined machine learning model indicates that the first user device is not authorized to perform the image capture at the current location of the first user device, restricting the first user device from performing the image capture; and

in response to a determination that the output of the predetermined machine learning model indicates that the first user device is authorized to perform the image capture at the current location of the first user device, allowing the first user device to perform the image capture.

2 . The CIM of claim 1 , wherein the location data and the camera data are captured, using an application installed on the first user device, wherein the location data is selected from the group consisting of: a geographical position system (GPS) location of the first user device, a location of the first user device within a predetermined building, and a location of the first user device with respect to a predetermined object of a predetermined secure process.

3 . The CIM of claim 1 , wherein the camera data is selected from the group consisting of: whether the first user device is currently being touched by the first user, whether an application of a predetermined type is open on the first user device, and whether a display of the first user device is on.

4 . The CIM of claim 1 , wherein enacting the first policy includes: collecting behavior data associated with the first user; and causing the predetermined machine learning model to use the behavior data to determine whether the first user device is authorized to perform the image capture, wherein the behavior data details a degree that the first user complies with predetermined policies of a predetermined company.

5 . The CIM of claim 4 , wherein enacting the first policy includes: determining a first weight for the location data; determining a second weight for the camera data; determining a third weight for the behavior data, wherein each of the weights are different from one another; and causing the predetermined machine learning model to apply the weights to the different types of data for determining whether the first user device is authorized to perform the image capture.

6 . The CIM of claim 4 , wherein enacting the first policy includes: in response to a determination that the current location of the first user device is within a predetermined proximity to a first secure area, outputting an invitation for enrolling the first user device with the first policy; in response to a determination that the first user device is enrolled with the first policy, allowing the first user device within the first secure area; and in response to a determination that the first user device is not enrolled with the first policy, preventing the first user device to enter within the first secure area.

7 . The CIM of claim 1 , wherein enacting the first policy includes: maintaining a separation of duties (SOD) matrix for a plurality of users including the first user, wherein the separation of duties matrix defines user roles and authorized responsibilities on a task by task basis for the plurality of users; and causing the predetermined machine learning model to use the SOD matrix for determining whether the first user device is authorized to perform the image capture.

8 . The CIM of claim 1 , wherein determining whether the first user device is authorized to perform the image capture at the current location of the first user device includes: tracking progress of a predetermined process that occurs within a first secure area, wherein the first user device is allowed to perform the image capture during a first portion of the predetermined process in response to the determination that the output of the predetermined machine learning model indicates that the first user device is authorized to perform the image capture at the current location, wherein the first user device is not allowed to perform the image capture during a remaining portion of the predetermined process.

9 . The CIM of claim 1 , wherein determining whether the first user device is authorized to perform the image capture at the current location of the first user device includes: in response to a determination that the current location of the first user device is in an unrestricted area, allowing the first user device to perform the image capture, wherein restricting the first user device from performing the image capture includes causing blurring to be applied to a background of an image displayed on a display of the first user device.

10 . A computer program product (CPP), the CPP comprising:

a set of one or more computer-readable storage media;

program instructions, collectively stored in the set of one or more storage media, for causing a processor set to perform the following computer operations:

enact a first policy for preventing unauthorized photo capture in sensitive areas, wherein enacting the first policy includes:

collecting location data and camera data for a first user device, wherein the first user device is associated with a user profile of a first user;

causing a predetermined machine learning model to use the location data and the camera data to determine whether the first user device is authorized to perform an image capture at a current location of the first user device;

in response to a determination that an output of the predetermined machine learning model indicates that the first user device is not authorized to perform the image capture at the current location of the first user device, restricting the first user device from performing the image capture; and

in response to a determination that the output of the predetermined machine learning model indicates that the first user device is authorized to perform the image capture at the current location of the first user device, allowing the first user device to perform the image capture.

11 . The CPP of claim 10 , wherein the location data and the camera data are captured, using an application installed on the first user device, wherein the location data is selected from the group consisting of: a geographical position system (GPS) location of the first user device, a location of the first user device within a predetermined building, and a location of the first user device with respect to a predetermined object of a predetermined secure process.

12 . The CPP of claim 10 , wherein the camera data is selected from the group consisting of: whether the first user device is currently being touched by the first user, whether an application of a predetermined type is open on the first user device, and whether a display of the first user device is on.

13 . The CPP of claim 10 , wherein enacting the first policy includes: collecting behavior data associated with the first user; and causing the predetermined machine learning model to use the behavior data to determine whether the first user device is authorized to perform the image capture, wherein the behavior data details a degree that the first user complies with predetermined policies of a predetermined company.

14 . The CPP of claim 13 , wherein enacting the first policy includes: determining a first weight for the location data; determining a second weight for the camera data; determining a third weight for the behavior data, wherein each of the weights are different from one another; and causing the predetermined machine learning model to apply the weights to the different types of data for determining whether the first user device is authorized to perform the image capture.

15 . The CPP of claim 13 , wherein enacting the first policy includes: in response to a determination that the current location of the first user device is within a predetermined proximity to a first secure area, outputting an invitation for enrolling the first user device with the first policy; in response to a determination that the first user device is enrolled with the first policy, allowing the first user device within the first secure area; and in response to a determination that the first user device is not enrolled with the first policy, preventing the first user device to enter within the first secure area.

16 . The CPP of claim 10 , wherein enacting the first policy includes: maintaining a separation of duties (SOD) matrix for a plurality of users including the first user, wherein the separation of duties matrix defines user roles and authorized responsibilities on a task by task basis for the plurality of users; and causing the predetermined machine learning model to use the SOD matrix for determining whether the first user device is authorized to perform the image capture.

17 . The CPP of claim 10 , wherein determining whether the first user device is authorized to perform the image capture at the current location of the first user device includes: tracking progress of a predetermined process that occurs within a first secure area, wherein the first user device is allowed to perform the image capture during a first portion of the predetermined process in response to the determination that the output of the predetermined machine learning model indicates that the first user device is authorized to perform the image capture at the current location, wherein the first user device is not allowed to perform the image capture during a remaining portion of the predetermined process.

18 . The CPP of claim 10 , wherein determining whether the first user device is authorized to perform the image capture at the current location of the first user device includes: in response to a determination that the current location of the first user device is in an unrestricted area, allowing the first user device to perform the image capture, wherein restricting the first user device from performing the image capture includes causing blurring to be applied to a background of an image displayed on a display of the first user device.

19 . A computer system (CS), the CS comprising:

a processor set;

a set of one or more computer-readable storage media;

program instructions, collectively stored in the set of one or more storage media, for causing the processor set to perform the following computer operations:

enact a first policy for preventing unauthorized photo capture in sensitive areas, wherein enacting the first policy includes:

collecting location data and camera data for a first user device, wherein the first user device is associated with a user profile of a first user;

causing a predetermined machine learning model to use the location data and the camera data to determine whether the first user device is authorized to perform an image capture at a current location of the first user device;

in response to a determination that an output of the predetermined machine learning model indicates that the first user device is not authorized to perform the image capture at the current location of the first user device, restricting the first user device from performing the image capture; and

in response to a determination that the output of the predetermined machine learning model indicates that the first user device is authorized to perform the image capture at the current location of the first user device, allowing the first user device to perform the image capture.

20 . The CS of claim 19 , wherein the location data and the camera data are captured, using an application installed on the first user device, wherein the location data is selected from the group consisting of: a geographical position system (GPS) location of the first user device, a location of the first user device within a predetermined building, and a location of the first user device with respect to a predetermined object of a predetermined secure process.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 26, 2024
From: FOX, JEREMY R.; KEEN, MARTIN G.; BREW, KEVIN W.; REZNICEK, ALEXANDER
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 066262/0302 →
Continuity (1)
Related Publication 20250240518A1 · Jul 24, 2025
References Cited (23)
US 10044464B1 · Bostick · 2018 [cited by examiner]
US 10178741B1 · Shah · 2019 [cited by examiner]
US 10915995B2 · Moloney · 2021 [cited by examiner]
US 11544962B2 · Sobh et al. · 2023 [cited by applicant]
US 20120260307A1 · Sambamurthy et al. · 2012 [cited by applicant]
US 20210034741A1 · Beveridge · 2021 [cited by examiner]
US 20210157933A1 · Turano · 2021 [cited by examiner]
US 20220043890A1 · Choi · 2022 [cited by applicant]
US 20220068058A1 · Kojima et al. · 2022 [cited by applicant]
US 20220075989A1 · Kimhi · 2022 [cited by examiner]
US 20220374130A1 · Pu et al. · 2022 [cited by applicant]
You, M., “An Adaptive Machine Learning Framework for Access Control Decision Making,” Thesis, Institute for Sustainable Industries and Liveable Cities, Victoria University, Feb. 2022, 97 pages, retrieved from https://vu… [cited by applicant]
Jiang et al., “Risk and UCON?based access control model for healthcare big data,” Journal of Big Data, 2023, pp. 1-28. [cited by applicant]
Kandala et al., “An Attribute Based Framework for Risk-Adaptive Access Control Models,” Sixth International Conference on Availability, Reliability and Security (ARES), 2011, 6 pages, retrieved from https://www.semantic… [cited by applicant]
Lufei et al., “Adaptive Secure Access to Remote Services,” IEEE International Conference on Services Computing, 2008, pp. 173-181. [cited by applicant]
Faaborg et al., “Security System with Authentication Code and Adaptive Photo Log,” IP.com Prior Art Database, Technical Disclosure No. IPCOM000250874D, Sep. 11, 2017, 12 pages. [cited by applicant]
Anonymous, “Improved White Balance Based on Multiple Photos of Same Subjects,” IP.com Prior Art Database, Technical Disclosure No. IPCOM000255937D, Oct. 24, 2018, 14 pages. [cited by applicant]
Anonymous, “Predicted Image-Capture Device Settings through Machine Learning,” IP.com Prior Art Database, Technical Disclosure No. IPCOM000258052D, Apr. 3, 2019, 9 pages. [cited by applicant]
Anonymous, “Contextually Adaptive Camera Parameter Reconfiguration Optimality,” IP.com Prior Art Database, Technical Disclosure No. IPCOM000265863D, May 20, 2021, 7 pages. [cited by applicant]
IBM, “Data privacy solutions,” IBM, 2023, 10 pages, retrieved from https://www.ibm.com/data-privacy on Jan. 19, 2024. [cited by applicant]
SafePaaS, “Segregation of Duties Audit Handbook, ERP Access Controls Testing,” SafePaaS, 2024, 21 pages, retrieved from https://www.safepaas.com/resources/Segregation_of_Duties_Handbook_for_ERP_Auditors.pdf. [cited by applicant]
“IBM Privacy Statement”, IBM, Oct. 30, 2025, 22 pages, https://www.ibm.com/us-en/privacy. [cited by applicant]
IBM “Media Center”, Oct. 30, 2025, 04 pages, https://newsroom.ibm.com/media-center-I1. [cited by applicant]