Legislating autonomous vehicles against the backdrop of adversarial machine learning findings

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Recent studies on adversarial machine learning1 made Michael Grossman, a Texas-based injury lawyer, skeptical of the viability of autonomous vehicles.2 These studies had pointed out that adversarial attacks or perturbations on pictures makes it difficult for the algorithm to correctly classify the content of that picture. If this is applied to traffic sign recognition, simple graffiti on the sign could mislead the algorithm that is analyzing the picture of the traffic sign captured by the camera. 3 Rather than recognizing the traffic sign for what it is, the algorithm could attribute a different meaning to the traffic sign. The consequences could be disastrous, especially if, for example, a stop sign would be read as a speeding sign.4 When rational car manufacturers know this defect, they will not proceed with the marketing of autonomous vehicles.

Original languageEnglish
Title of host publication2019 8th IEEE International Conference on Connected Vehicles and Expo, ICCVE 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728101422
DOIs
Publication statusPublished - Nov 2019
Event8th IEEE International Conference on Connected Vehicles and Expo, ICCVE 2019 - Graz, Austria
Duration: Nov 4 2019Nov 8 2019

Publication series

Name2019 8th IEEE International Conference on Connected Vehicles and Expo, ICCVE 2019 - Proceedings

Conference

Conference8th IEEE International Conference on Connected Vehicles and Expo, ICCVE 2019
Country/TerritoryAustria
CityGraz
Period11/4/1911/8/19

All Science Journal Classification (ASJC) codes

  • Control and Optimization
  • Transportation
  • Computer Networks and Communications
  • Automotive Engineering

Fingerprint

Dive into the research topics of 'Legislating autonomous vehicles against the backdrop of adversarial machine learning findings'. Together they form a unique fingerprint.

Cite this