Robustness Analysis on Natural Language Processing Based AI Q&A Robots

  • Chengxiang Yuan
  • , Mingfu Xue*
  • , Lingling Zhang
  • , Heyi Wu
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Recently, the natural language processing (NLP) based intelligent question and answering (Q&A) robots have been used in a wide range of applications, such as smart assistant, smart customer service, government business. However, the robustness and security issues of these NLP based artificial intelligence (AI) Q&A robots have not been studied yet. In this paper, we analyze the robustness problems in current Q&A robots, which include four aspects: (1) semantic slot settings are incomplete; (2) sensitive words are not filtered efficiently and completely; (3) Q&A robots return the search results directly; (4) unsatisfactory matching algorithms and inappropriate matching threshold settings. Then, we design and implement two types of evaluation tests, bad language and user’s typos, to evaluate the robustness of several state-of-the-art Q&A robots. Experiment results show that these common inputs (bad language and user’s typos) can successfully make these Q&A robots malfunction, denial of service, or speaking dirty words. Besides, we also propose possible countermeasures to enhance the robustness of these Q&A robots. To the best of the authors’ knowledge, this is the first work on analyzing the robustness and security problems of intelligent Q&A robots. This work can hopefully help provide guidelines to design robust and secure Q&A robots.

Original languageEnglish
Title of host publicationMachine Learning and Intelligent Communications - 4th International Conference, MLICOM 2019, Proceedings
EditorsXiangping Bryce Zhai, Bing Chen, Kun Zhu
PublisherSpringer
Pages695-711
Number of pages17
ISBN (Print)9783030323875
DOIs
StatePublished - 2019
Externally publishedYes
Event4th International Conference on Machine Learning and Intelligent Communications, MLICOM 2019 - Nanjing, China
Duration: 24 Aug 201925 Aug 2019

Publication series

NameLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume294 LNCIST
ISSN (Print)1867-8211

Conference

Conference4th International Conference on Machine Learning and Intelligent Communications, MLICOM 2019
Country/TerritoryChina
CityNanjing
Period24/08/1925/08/19

Keywords

  • AI security
  • Natural language processing
  • Question and answer robots
  • Robustness

Fingerprint

Dive into the research topics of 'Robustness Analysis on Natural Language Processing Based AI Q&A Robots'. Together they form a unique fingerprint.

Cite this