On the feasibility of attacking Thai LPR systems with adversarial examples

TL;DR

This paper investigates the vulnerability of Thai License Plate Recognition systems to adversarial attacks, demonstrating high success rates and introducing a semi-targeted attack scenario specific to Thai OCR applications.

Contribution

It is the first study to evaluate adversarial attacks on Thai OCR, proposing a semi-targeted attack method tailored for Thai LPR systems.

Findings

Over 90% attack success rate on Thai LPR systems

Feasibility of attacks on standard desktop computers

Introduction of a semi-targeted attack scenario for Thai OCR

Abstract

Recent advances in deep neural networks (DNNs) have significantly enhanced the capabilities of optical character recognition (OCR) technology, enabling its adoption to a wide range of real-world applications. Despite this success, DNN-based OCR is shown to be vulnerable to adversarial attacks, in which the adversary can influence the DNN model's prediction by carefully manipulating input to the model. Prior work has demonstrated the security impacts of adversarial attacks on various OCR languages. However, to date, no studies have been conducted and evaluated on an OCR system tailored specifically for the Thai language. To bridge this gap, this work presents a feasibility study of performing adversarial attacks on a specific Thai OCR application -- Thai License Plate Recognition (LPR). Moreover, we propose a new type of adversarial attack based on the \emph{semi-targeted} scenario and show that this scenario is highly realistic in LPR applications. Our experimental results show the feasibility of our attacks as they can be performed on a commodity computer desktop with over 90% attack success rate.