IP Library › Granted Patent US 12,512,959
Granted Patent B2
US 12,512,959 · App. 18/498,677 · Granted Dec 30, 2025

Optical encryption camera

Inventors: Francesco Pittaluga (Los Angeles, CA); Xiang Yu (Mountain View, CA); Salman Khan (San Jose, CA)
Assignee: NEC Corporation
H04L9/002G06F21/602G06V40/172H04L9/0869H04N25/10
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 12,512,959
App. No.
18/498,677
Granted
Dec 30, 2025
Kind
B2
Abstract

An optical encryption camera includes a sensor array and a filter positioned over the sensor array to receive light prior to the sensor array. The filter includes a multiplexing mask and a scaling mask in sequence. The multiplexing mask and the scaling mask combine to provide an encryption key to encrypt image data prior to capture.

Claims (32)

1 . An optical encryption camera, comprising:

a sensor array;

a filter positioned over the sensor array to receive light prior to the sensor array, the filter including:

a multiplexing mask and a scaling mask in sequence, the multiplexing mask and the scaling mask combining to provide an encryption key to encrypt image data prior to capture; and

a mask generator training module to generate masks resistant to a range of cyber-attacks.

2 . The optical encryption camera of claim 1 , further comprising a connectable decryption module to decrypt encrypted image data by inverse operation of the multiplexing mask and the scaling mask.

3 . The optical encryption camera of claim 1 , wherein the multiplexing mask and the scaling mask are randomly generated using seeds.

4 . The optical encryption camera of claim 1 , wherein the mask generator training module is optimized in accordance with an adversarial loss function.

5 . The optical encryption camera of claim 4 , wherein the adversarial loss function is minimized for reconstruction error to measure decryption accuracy.

6 . The optical encryption camera of claim 4 , wherein the adversarial loss function is maximized for reconstruction error for blind decryption.

7 . The optical encryption camera of claim 1 , wherein the mask generator training module further comprises at least one mask generator trained using a deep learning neural network.

8 . The optical encryption camera of claim 1 , wherein the mask generator training module further comprises a blind decryption module trained using a deep learning neural network.

9 . The optical encryption camera of claim 1 , wherein the optical encryption camera captures medical images including sensitive data and the sensitive data is stored in memory in an encrypted state.

10 . The optical encryption camera of claim 1 , wherein the optical encryption camera captures face images to perform face recognition using images in an encrypted state.

11 . A method for optical encryption, comprising:

training a mask generator training module by employing keyed and blind simulations of input images to generate masks resistant to a range of cyber-attacks;

encrypting an image, by an optical encryption camera, by applying a multiplexing mask to the image and applying a scaling mask to the image to provide an encrypted image;

receiving the encrypted image on a sensor array wherein the multiplexing mask and the scaling mask combine to provide an encryption key to encrypt image data prior to capture; and

storing the encrypted image.

12 . The method of claim 11 , further comprising decrypting the encrypted image to provide a decrypted image using a connectable decryption module by employing inverse operations of the multiplexing mask and the scaling mask.

13 . The method of claim 12 , further comprising displaying the decrypted image.

14 . The method of claim 11 , wherein the multiplexing mask and the scaling mask are randomly generated using seeds.

15 . The method of claim 11 , wherein the mask generator training module is optimized in accordance with an adversarial loss function,

wherein the adversarial loss function is minimized for reconstruction error to measure decryption accuracy; and

wherein the adversarial loss function is maximized for reconstruction error for blind decryption.

16 . The method of claim 11 , wherein the mask generator training module further comprises at least one mask generator trained using a deep learning neural network.

17 . The method of claim 11 , wherein the optical encryption camera captures medical images including sensitive data and the sensitive data is stored in memory in an encrypted state.

18 . The method of claim 11 , wherein the optical encryption camera captures face images to perform face recognition using images in an encrypted state.

19 . An optical encryption camera, comprising:

a sensor array; and

a filter positioned over the sensor array to receive light prior to the sensor array, the filter including:

a multiplexing mask and a scaling mask in sequence, the multiplexing mask and the scaling mask combining to provide an encryption key to encrypt image data prior to capture, wherein the multiplexing mask and the scaling mask are randomly generated using seeds.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 18, 2025
From: NEC LABORATORIES AMERICA, INC.
To: NEC CORPORATION
Reel/Frame 072938/0913 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 31, 2023
From: PITTALUGA, FRANCESCO; YU, XIANG; KHAN, SALMAN
To: NEC LABORATORIES AMERICA, INC.
Reel/Frame 065406/0659 →
Continuity (5)
Provisional Application 63460056 · Apr 18, 2023
Provisional Application 63423077 · Nov 7, 2022
Provisional Application 63423076 · Nov 7, 2022
Provisional Application 63421674 · Nov 2, 2022
Related Publication 20240154784A1 · May 9, 2024
References Cited (10)
US 20170366763A1 · Lin · 2017 [cited by examiner]
Byrne, J., DeCann, B., & Bloom, S. (Sep. 11, 2020). Key-nets: Optical transformation convolutional networks for privacy preserving vision sensors. arXiv preprint arXiv:2008.04469. [cited by applicant]
Nguyen Canh, T., & Nagahara, H. (Jun. 15, 2019). Deep compressive sensing for visual privacy protection in flatcam imaging. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (pp. 0-0). [cited by applicant]
Ishii, Y., Sato, S., & Yamashita, T. (Aug. 23, 2020). Privacy-aware face recognition with lensless multi-pinhole camera. In Computer Vision—ECCV 2020 Workshops: Glasgow, UK, Proceedings, Part V 16 (pp. 476-493). Springe… [cited by applicant]
Liao, M., Zheng, S., Pan, S., Lu, D., He, W., Situ, G., & Peng, X. (May 20, 2021). Deep-learning-based ciphertext-only attack on optical double random phase encryption. Opto-Electronic Advances, 4(5), 200016-1. [cited by applicant]
Wang, Y., Gawedzinski, J., Pawlowski, M. E., & Tkaczyk, T. S. (Jun. 11, 2018). 3D printed fiber optic faceplates by custom controlled fused deposition modeling. Optics Express, 26(12), 15362-15376. [cited by applicant]
Wang, Z. W., Vineet, V., Pittaluga, F., Sinha, S. N., Cossairt, O., & Bing Kang, S. (Jun. 15, 2019). Privacy-preserving action recognition using coded aperture videos. In Proceedings of the IEEE/CVF Conference on Comput… [cited by applicant]
Liao, M., He, W., Lu, D., & Peng, X. (Jan. 31, 2017). Ciphertext-only attack on optical cryptosystem with spatially incoherent illumination: from the view of imaging through scattering medium. Scientific Reports, 7(1), … [cited by applicant]
Refregier, P., & Javidi, B. (Apr. 1, 1995). Optical image encryption based on input plane and Fourier plane random encoding. Optics letters, 20(7), 767-769. [cited by applicant]
Zang, J., Xie, Z., & Zhang, Y. (Apr. 15, 2013). Optical image encryption with spatially incoherent illumination. Optics letters, 38(8), 1289-1291. [cited by applicant]