The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
인터넷상의 악의적인 공격자는 자동화된 공격 프로그램을 이용하여 대량 스팸, 불필요한 게시판 게시, 계정 생성 등을 통해 서비스 이용을 방해합니다. 이러한 자동화된 공격을 방지하기 위한 보안 솔루션으로 컴퓨터와 인간을 구별하는 완전 자동화된 공개 튜링 테스트(CAPTCHA)가 사용됩니다. CAPTCHA는 인간만이 이해할 수 있는 왜곡된 문자, 음성, 이미지를 제공하여 사용자가 기계인지 사람인지를 판별하는 시스템입니다. 그러나 광학문자인식(OCR), 심층신경망(DNN) 등 새로운 공격 기법이 CAPTCHA를 우회하는 데 사용됐다. 본 논문에서는 FGSM(Fast-Gradient Sign Method), I-FGSM(Iterative FGSM), DeepFool 방법을 이용하여 CAPTCHA 이미지를 생성하는 방법을 제안한다. 데이터세트로는 Python에서 제공하는 CAPTCHA 이미지를, 머신러닝 라이브러리로는 Tensorflow를 사용했습니다. 실험 결과는 FGSM, I-FGSM, DeepFool 방법을 통해 생성된 CAPTCHA 이미지가 FGSM의 경우 ε=0로 0.15% 인식률을 나타내고, I-FGSM의 경우 0회 반복으로 α=0.1로 50% 인식률을 나타냄을 보여줍니다. DeepFool 방법의 경우 45회 반복으로 150%의 인식률을 보였습니다.
Hyun KWON
Korea Advanced Institute of Science and Technology,Korea Military Academy
Hyunsoo YOON
Korea Advanced Institute of Science and Technology
Ki-Woong PARK
Sejong University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Hyun KWON, Hyunsoo YOON, Ki-Woong PARK, "Robust CAPTCHA Image Generation Enhanced with Adversarial Example Methods" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 4, pp. 879-882, April 2020, doi: 10.1587/transinf.2019EDL8194.
Abstract: Malicious attackers on the Internet use automated attack programs to disrupt the use of services via mass spamming, unnecessary bulletin boarding, and account creation. Completely automated public turing test to tell computers and humans apart (CAPTCHA) is used as a security solution to prevent such automated attacks. CAPTCHA is a system that determines whether the user is a machine or a person by providing distorted letters, voices, and images that only humans can understand. However, new attack techniques such as optical character recognition (OCR) and deep neural networks (DNN) have been used to bypass CAPTCHA. In this paper, we propose a method to generate CAPTCHA images by using the fast-gradient sign method (FGSM), iterative FGSM (I-FGSM), and the DeepFool method. We used the CAPTCHA image provided by python as the dataset and Tensorflow as the machine learning library. The experimental results show that the CAPTCHA image generated via FGSM, I-FGSM, and DeepFool methods exhibits a 0% recognition rate with ε=0.15 for FGSM, a 0% recognition rate with α=0.1 with 50 iterations for I-FGSM, and a 45% recognition rate with 150 iterations for the DeepFool method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8194/_p
부
@ARTICLE{e103-d_4_879,
author={Hyun KWON, Hyunsoo YOON, Ki-Woong PARK, },
journal={IEICE TRANSACTIONS on Information},
title={Robust CAPTCHA Image Generation Enhanced with Adversarial Example Methods},
year={2020},
volume={E103-D},
number={4},
pages={879-882},
abstract={Malicious attackers on the Internet use automated attack programs to disrupt the use of services via mass spamming, unnecessary bulletin boarding, and account creation. Completely automated public turing test to tell computers and humans apart (CAPTCHA) is used as a security solution to prevent such automated attacks. CAPTCHA is a system that determines whether the user is a machine or a person by providing distorted letters, voices, and images that only humans can understand. However, new attack techniques such as optical character recognition (OCR) and deep neural networks (DNN) have been used to bypass CAPTCHA. In this paper, we propose a method to generate CAPTCHA images by using the fast-gradient sign method (FGSM), iterative FGSM (I-FGSM), and the DeepFool method. We used the CAPTCHA image provided by python as the dataset and Tensorflow as the machine learning library. The experimental results show that the CAPTCHA image generated via FGSM, I-FGSM, and DeepFool methods exhibits a 0% recognition rate with ε=0.15 for FGSM, a 0% recognition rate with α=0.1 with 50 iterations for I-FGSM, and a 45% recognition rate with 150 iterations for the DeepFool method.},
keywords={},
doi={10.1587/transinf.2019EDL8194},
ISSN={1745-1361},
month={April},}
부
TY - JOUR
TI - Robust CAPTCHA Image Generation Enhanced with Adversarial Example Methods
T2 - IEICE TRANSACTIONS on Information
SP - 879
EP - 882
AU - Hyun KWON
AU - Hyunsoo YOON
AU - Ki-Woong PARK
PY - 2020
DO - 10.1587/transinf.2019EDL8194
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2020
AB - Malicious attackers on the Internet use automated attack programs to disrupt the use of services via mass spamming, unnecessary bulletin boarding, and account creation. Completely automated public turing test to tell computers and humans apart (CAPTCHA) is used as a security solution to prevent such automated attacks. CAPTCHA is a system that determines whether the user is a machine or a person by providing distorted letters, voices, and images that only humans can understand. However, new attack techniques such as optical character recognition (OCR) and deep neural networks (DNN) have been used to bypass CAPTCHA. In this paper, we propose a method to generate CAPTCHA images by using the fast-gradient sign method (FGSM), iterative FGSM (I-FGSM), and the DeepFool method. We used the CAPTCHA image provided by python as the dataset and Tensorflow as the machine learning library. The experimental results show that the CAPTCHA image generated via FGSM, I-FGSM, and DeepFool methods exhibits a 0% recognition rate with ε=0.15 for FGSM, a 0% recognition rate with α=0.1 with 50 iterations for I-FGSM, and a 45% recognition rate with 150 iterations for the DeepFool method.
ER -