Operating light sources to project patterns for disorienting visual detection systems

Patent metadata

Field	Value
Publication number	US-11543502-B2
Application number	US-201916519015-A
Country	US
Kind code	B2
Filing date	Jul 23, 2019
Priority date	Jul 23, 2019
Publication date	Jan 3, 2023
Grant date	Jan 3, 2023

Abstract

Methods and systems fort operating one or more light sources to project adversarial patterns generated to disorient a machine learning based detection system, comprising generating one or more adversarial patterns configured to disorient the machine learning based detection system and operating one or more light sources configured to project one or more of the adversarial pattern(s) in association with the targeted object in order to disorient the machine learning based detection system.

First claim

What is claimed is:

1. A method of operating at least one light source to project adversarial patterns generated to disorient a machine learning based detection system, comprising:
using at least one processor associated with an object targeted by the machine learning based detection system, the at least one processor is used for:
generating at least one adversarial pattern configured to disorient the machine learning based detection system; and
operating the at least one light source configured to project the at least one adversarial pattern in association with the targeted object in order to disorient the machine learning based detection system,

wherein the machine learning based detection system is a machine learning based acquisition system of an incoming weapon projectile targeting the object, the at least one adversarial pattern is configured to disorient the machine learning based acquisition system in order to prevent the incoming weapon projectile from locking on the targeted object.

2. The method of claim 1 , wherein the at least one light source includes a plurality of distinct spot light sources distributed over the targeted object.

3. The method of claim 1 , wherein the at least one light source includes a screen.

4. The method of claim 1 , wherein the at least one light source includes a hologram projector.

5. The method of claim 1 , wherein the at least one light source is mounted on the object.

6. The method of claim 1 , wherein the targeted object is a member of a group consisting of: a person, a ground vehicle, an aerial vehicle, a naval vehicle and a structure.

7. The method of claim 1 , wherein the machine learning based detection system is a machine learning based face recognition system attempting to identify a face of a human object, the at least one adversarial pattern is configured to disorient the machine learning based face recognition system in order to prevent identification of the human object.

8. A system for operating at least one light source to project adversarial patterns generated to disorient a machine learning based detection system, comprising:
the at least one light source configured to project patterns in association with an object targeted by the machine learning based detection system;
at least one processor associated with the object and coupled to the at least one light source, the at least one processor is adapted to execute a code, the code comprising:
code instructions to generate at least one adversarial pattern configured to disorient the machine learning based detection system, and
code instructions to operate the at least one light source to project the at least one adversarial pattern in association with the object in order to disorient the machine learning based detection system targeting the object,

wherein the machine learning based detection system is a machine learning based acquisition system of an incoming weapon projectile targeting the object, the at least one adversarial pattern is configured to disorient the machine learning based acquisition system in order to prevent the incoming weapon projectile from locking on the targeted object.

Assignees

• Nec Corp America

Inventors

• Hoch Yaacov
• Lev Tsvi

Classifications

• G01S7/495 Primary

  Counter-measures or counter-counter-measures {using electronic or electro-optical means} · CPC title

• G06N20/00

  Machine learning · CPC title

• F41H3/00 Primary

  Camouflage, i.e. means or methods for concealment or disguise (for vessels B63G8/34, B63G13/02 {; sound camouflage, i.e. simulating gun fire noise, F41A33/04; dummy or decoy targets F41J; chaff per se F41J2/00; ammunition for dispensing chaff F42B5/15, F42B12/70; radar absorbing fabrics H01Q17/005}) · CPC title

• G03B15/02

  Illuminating scene · CPC title

• G06F2218/00

  Aspects of pattern recognition specially adapted for signal processing · CPC title