IP Library › Granted Patent US 12,567,246
Granted Patent B2
US 12,567,246 · App. 18/051,578 · Granted Mar 3, 2026

Fair neural networks

Inventors: Xinru Hua (Redwood City, CA); Huanzhong Xu (Stanford, CA); Jose Blanchet (Palo Alto, CA); Viet Anh Nguyen (Hanoi, VN); Marcos Paul Gerardo Castro (San Francisco, CA)
Assignees: Ford Global Technologies, LLC; The Board of Trustees of the Leland Stanford Junior University
G06V10/82G06T7/70G06V10/761G06T2207/20081
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 12,567,246
App. No.
18/051,578
Granted
Mar 3, 2026
Kind
B2
Abstract

A system is disclosed that includes a computer that includes a processor and a memory, the memory including instructions executable by the processor to input an image acquired by a sensor to a neural network to output a prediction regarding an object included in the image. The neural network can be trained based on (a) a distributed robust optimization that minimizes an expectation applied to probability distributions of loss functions to select training images that yield a solution with a selected uncertainty level and (b) generating additional input images based on adversarial images.

Claims (25)

1 . A system, comprising:

a computer that includes a processor and a memory, the memory including instructions executable by the processor to:

input an image acquired by a sensor to a neural network to output a prediction regarding an object included in the image; and

wherein the neural network is trained based on (a) a distributed robust optimization that minimizes an expectation applied to probability distributions of loss functions to adversarial training images that yield a solution with a selected uncertainty level and (b) generating additional input images based on the adversarial images; wherein the additional input images are generated based on a structural similarity index measure.

2 . The system of claim 1 , wherein outputting the prediction regarding the image includes outputting an object identity and an object location.

3 . The system of claim 1 , wherein the neural network outputs a confidence value that indicates a probability that the prediction regarding the image is correct.

4 . The system of claim 1 , wherein the loss function is determined based on comparing output from the neural network with ground truth data based on the input image.

5 . The system of claim 1 , wherein the neural network includes convolutional layers and fully connected layers.

6 . The system of claim 1 , wherein the input images are respectively input to the neural network a plurality of times and the loss functions are backpropagated through layers of the neural network to select weights that minimize the loss functions.

7 . The system of claim 1 , wherein generating the additional input images based on the adversarial images includes determining imperceptible differences based on the structural similarity index measure.

8 . The system of claim 7 , wherein the structural similarity index measure generates images that are not perceptibly different to a human observer but can cause the neural network to fail.

9 . The system of claim 1 , wherein generating the additional input images based on the adversarial images includes determining imperceptible differences based on processing the input image with a PieAPP neural network.

10 . The system of claim 9 , wherein the PieAPP neural network generates images that are not perceptibly different to a human observer but can cause the neural network to fail.

11 . A method, comprising:

inputting an image acquired by a sensor to a neural network to output a prediction regarding an object included in the image; and

wherein the neural network is trained based on (a) a distributed robust optimization that minimizes an expectation applied to probability distributions of loss functions to adversarial training images that yield a solution with a selected uncertainty level and (b) generating additional input images based on the adversarial images; wherein the additional input images are generated based on a structural similarity index measure.

12 . The method of claim 11 , wherein outputting the prediction regarding the image includes outputting an object identity and an object location.

13 . The method of claim 11 , wherein the neural network outputs a confidence value that indicates a probability that the prediction regarding the image is correct.

14 . The method of claim 11 , wherein the loss function is determined based on comparing output from the neural network with ground truth data based on the input image.

15 . The method of claim 11 , wherein the neural network includes convolutional layers and fully connected layers.

16 . The method of claim 11 , wherein the input images are respectively input to the neural network a plurality of times and the loss functions are backpropagated through layers of the neural network to select weights that minimize the loss functions.

17 . The method of claim 11 , wherein generating the additional input images based on the adversarial images includes determining imperceptible differences based on the structural similarity index measure.

18 . The method of claim 17 , wherein the structural similarity index measure generates images that are not perceptibly different to a human observer but can cause the neural network to fail.

19 . The method of claim 11 , wherein generating the additional input images based on the adversarial images includes determining imperceptible differences based on processing the input image with a PieAPP neural network.

20 . The method of claim 19 , wherein the PieAPP neural network generates images that are not perceptibly different to a human observer but can cause the neural network to fail.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 1, 2022
From: HUA, XINRU; XU, HUANZHONG; BLANCHET, JOSE; NGUYEN, VIET ANH; GERARDO CASTRO, MARCOS PAUL
To: FORD GLOBAL TECHNOLOGIES, LLC; THE BOARD OF TRUSTEES OF THE LELAND STANFORD JUNIOR UNIVERSITY
Reel/Frame 061610/0226 →
Continuity (1)
Related Publication 20240144663A1 · May 2, 2024
References Cited (8)
US 20200051239A1 · Braun et al. · 2020 [cited by applicant]
US 20210357745A1 · Wallis et al. · 2021 [cited by applicant]
CN 112085194A · 2020 [cited by applicant]
Chen Y, Xu K, He D, Ban X. Generating robust real-time object detector with uncertainty via virtual adversarial training. International Journal of Machine Learning and Cybernetics. Feb. 2022;13(2):431-45. (Year: 2022). [cited by examiner]
Chen, Ruidi, Boran Hao, and Ioannis Paschalidis. “Distributionally robust multiclass classification and applications in deep cnn image classifiers.” stat 1050 (2021): 27. (Year: 2021). [cited by examiner]
Miyato, Takeru, et al. “Virtual adversarial training: a regularization method for supervised and semi-supervised learning.” IEEE transactions on pattern analysis and machine intelligence 41.8 (2019): 1979-1993. (Year: 2… [cited by examiner]
Liu Y, Jiang M, Jiang T. Transferable adversarial examples based on global smooth perturbations. Computers & Security. Oct. 1, 2022;121:102816. (Year: 2022). [cited by examiner]
Ren., A. et al., Distributionally Robust Policy Learning via Adversarial Environment Generation, swingarXiv:2107.06353v4 [cs.RO], Dec. 28, 2021, 11 pages. [cited by applicant]