Detection of whether a communication is generated via artificial intelligence
In an example embodiment, a software application is introduced that is able to automatically detect whether a conversation in a chat interface is with a human or an artificial intelligence. More specifically, the software application is able to identify how the chat interface is interacted with and replicate that mechanism to allow the software application to directly contact the other party (whether human or AI) on the other side of a chat conversation.
1. A system comprising:
at least one hardware processor;
a computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations comprising:
accessing a context of an online chat between a user and an unknown participant;
creating a communication channel directly between a testing application and the unknown participant, using the context;
using a first cluster of the testing application to send a first question to the unknown participant and measure speed at which the unknown participant responds;
generating a first score indicative of a likelihood that the unknown participant is an artificial intelligence (AI) component based on the speed;
using a second cluster of the testing application to send a second question combined with dynamically generated data to the unknown participant;
generating a second score indicative of a likelihood that the unknown participant is an AI component based on one or more responses to the second question;
using a third cluster of the testing application to send a third question combined with dynamically generated data to the unknown participant;
generating a third score indicative of a likelihood that the unknown participant is an AI component based on one or more responses to the third question;
using a fourth cluster of the testing application to send a fourth question combined with dynamically generated data to the unknown participant;
generating a fourth score indicative of a likelihood that the unknown participant is an AI component based on one or more responses to the fourth question; and
combining the first, second, third, and fourth scores.
2. The system of claim 1 , wherein the first question is a question designed to elicit a long response.
3. The system of claim 1 , wherein the second question is a question designed to check language-specific characteristics of a response.
4. The system of claim 1 , wherein the second question is a question asking facts about a recent news article.
5. The system of claim 1 , wherein the second question is a question asking facts about enterprise data.
6. The system of claim 1 , wherein the generating a second score comprises utilizing a first machine learning model trained by a first machine learning algorithm.
7. The system of claim 6 , wherein the generating a third score comprises utilizing a second machine learning model trained by a third machine learning algorithm.
8. The system of claim 7 , wherein the generating a fourth score comprises utilizing a third machine learning model trained by a third machine learning algorithm.
9. The system of claim 8 , wherein the combining comprises calculating a weighted average of the first score, second score, third score, and fourth score, wherein a weight assigned to each of the first score, second score, third score, and fourth score is learned by a fourth machine learning model based on the context.
10. A method comprising:
accessing a context of an online chat between a user and an unknown participant;
creating a communication channel directly between a testing application and the unknown participant, using the context;
using a first cluster of the testing application to send a first question to the unknown participant and measure speed at which the unknown participant responds;
generating a first score indicative of a likelihood that the unknown participant is an artificial intelligence (AI) component based on the speed;
using a second cluster of the testing application to send a second question combined with dynamically generated data to the unknown participant;
generating a second score indicative of a likelihood that the unknown participant is an AI component based on one or more responses to the second question;
using a third cluster of the testing application to send a third question combined with dynamically generated data to the unknown participant;
generating a third score indicative of a likelihood that the unknown participant is an AI component based on one or more responses to the third question;
using a fourth cluster of the testing application to send a fourth question combined with dynamically generated data to the unknown participant;
generating a fourth score indicative of a likelihood that the unknown participant is an AI component based on one or more responses to the fourth question; and
combining the first, second, third, and fourth scores.
11. The method of claim 10 , wherein the first question is a question designed to elicit a long response.
12. The method of claim 10 , wherein the second question is a question designed to check language-specific characteristics of a response.
13. The method of claim 10 , wherein the second question is a question asking facts about a recent news article.
14. The method of claim 10 , wherein the second question is a question asking facts about enterprise data.
15. The method of claim 10 , wherein the generating a second score comprises utilizing a first machine learning model trained by a first machine learning algorithm.
16. The method of claim 15 , wherein the generating a third score comprises utilizing a second machine learning model trained by a third machine learning algorithm.
17. The method of claim 16 , wherein the generating a fourth score comprises utilizing a third machine learning model trained by a third machine learning algorithm.
18. A non-transitory machine-readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising:
accessing a context of an online chat between a user and an unknown participant;
creating a communication channel directly between a testing application and the unknown participant, using the context;
using a first cluster of the testing application to send a first question to the unknown participant and measure speed at which the unknown participant responds;
generating a first score indicative of a likelihood that the unknown participant is an artificial intelligence (AI) component based on the speed;
using a second cluster of the testing application to send a second question combined with dynamically generated data to the unknown participant;
generating a second score indicative of a likelihood that the unknown participant is an AI component based on one or more responses to the second question;
using a third cluster of the testing application to send a third question combined with dynamically generated data to the unknown participant;
generating a third score indicative of a likelihood that the unknown participant is an AI component based on one or more responses to the third question;
using a fourth cluster of the testing application to send a fourth question combined with dynamically generated data to the unknown participant;
generating a fourth score indicative of a likelihood that the unknown participant is an AI component based on one or more responses to the fourth question; and
combining the first, second, third, and fourth scores.
19. The non-transitory machine-readable medium of claim 18 , wherein the first question is a question designed to elicit a long response.
20. The non-transitory machine-readable medium of claim 18 , wherein the second question is a question designed to check language-specific characteristics of a response.