Cognitive learning to counter security threats for kinematic actions in robots

Patent metadata

Field	Value
Publication number	US-10452842-B2
Application number	US-201715616586-A
Country	US
Kind code	B2
Filing date	Jun 7, 2017
Priority date	Jun 7, 2017
Publication date	Oct 22, 2019
Grant date	Oct 22, 2019

Abstract

A security control system for a kinematic robot uses a cognitive assessment agent to map proposed instructions to either legitimate or illegitimate actions based on contextual variables. The agent computes a security anomaly index score representing a variance of a likely kinematic action of the robot compared to acceptable actions. If the score exceeds a predetermined threshold, a security alert is generated for the robot's administrator. The contextual variables include a user profile, a user location, and subject matter of the kinematic actions. The analysis compares input text to predefined classification metadata, and can also compare verbal phrases or body gestures to corresponding baselines. Different numeric weights can be applied to the contextual variables. The computing begins with a default value for the score and thereafter increments or decrements the score based on the weights. The weights can be adjusted based on a supervisory appraisal of the computed score.

First claim

What is claimed is:

1. A computer system comprising:
one or more processors which process program instructions;
a memory device connected to said one or more processors; and
program instructions residing in said memory device for countering security threats for kinematic actions in robots by receiving input instructions for a kinematic robot, conducting an analysis of the input instructions using a cognitive system which maps proposed instructions to either legitimate behavioral actions or illegitimate behavioral actions based on contextual variables relating to a context of the input instructions, computing a security anomaly index score based on the analysis wherein the security anomaly index score represents a variance of a likely kinematic action of the kinematic robot in response to the input instructions compared to acceptable actions, different numeric weights are applied to the contextual variables, and the computing begins with a default value for the security anomaly index score and thereafter increments or decrements the security anomaly index score based on the weights, determining that the security anomaly index score exceeds a predetermined threshold, and responsively generating a security alert for an administrator of the kinematic robot.

2. The computer system of claim 1 wherein the contextual variables include a user profile, a user location, and subject matter of the kinematic actions.

3. The computer system of claim 1 wherein the analysis includes comparing one or more input phrases from the input instructions to predefined classification metadata.

4. The computer system of claim 1 wherein the analysis includes comparing one or more verbal phrases or body gestures to corresponding baselines.

5. The computer system of claim 1 wherein the input instructions are first input instructions, and said program instructions residing in said memory device further receive second input instructions for the kinematic robot, and repeat the conducting and the computing for the second input instructions while using different values for the weights.

6. The computer system of claim 1 wherein said program instructions residing in said memory device further receive a supervisory appraisal of the computed security anomaly index score, and adjust the weights based on the supervisory appraisal.

7. A computer program product comprising:
a computer readable storage medium; and
program instructions residing in said computer readable storage medium for countering security threats for kinematic actions in robots by receiving input instructions for a kinematic robot, conducting an analysis of the input instructions using a cognitive system which maps proposed instructions to either legitimate behavioral actions or illegitimate behavioral actions based on contextual variables relating to a context of the input instructions, computing a security anomaly index score based on the analysis wherein the security anomaly index score represents a variance of a likely kinematic action of the kinematic robot in response to the input instructions compared to acceptable actions, different numeric weights are applied to the contextual variables, and the computing begins with a default value for the security anomaly index score and thereafter increments or decrements the security anomaly index score based on the weights, determining that the security anomaly index score exceeds a predetermined threshold, and responsively generating a security alert for an administrator of the kinematic robot.

8. The computer program product of claim 7 wherein the contextual variables include a user profile, a user location, and subject matter of the kinematic actions.

9. The computer program product of claim 7 wherein the analysis includes comparing one or more input phrases from the input instructions to predefined classification metadata.

10. The computer program product of claim 7 wherein the analysis includes comparing one or more verbal phrases or body gestures to corresponding baselines.

11. The computer program product of claim 7 wherein the input instructions are first input instructions, and said program instructions further receive second input instructions for the kinematic robot, and repeat the conducting and the computing for the second input instructions while using different values for the weights.

Assignees

• IBM

Inventors

• Dhondse Amol A
• Pikle Anand
• Sivakumar Gandhi

Classifications

• G06F21/554

  involving event detection and direct action · CPC title

• B25J9/163

  learning, adaptive, model based, rule based expert control · CPC title

• G06F2221/034

  Test or assess a computer or a system · CPC title

• G05B13/0265

  the criterion being a learning criterion · CPC title

• G06N3/008

  based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour · CPC title