Abstract
In today’s digital age, image-based CAPTCHAs are increasingly vulnerable to attacks using annotation services, which tag images and classify images according to their contents, or reverse image search services. To prevent such attacks, an image-based CAPTCHA was proposed that takes advantage of the fact that humans can correctly recognize images containing many discontinuous points, while existing image recognition systems misrecognize them. However, this CAPTCHA proved susceptible to attacks using noise reduction filters. The objective of the present study is to create a CAPTCHA using images that are resistant to such filters. Images used in the new CAPTCHA were realized by increasing the proportion of lines forming discontinuous surfaces in images. Experimental results demonstrated a human recognition rate of 95.8%, with the image recognition systems successfully identifying only one image overall. Moreover, when a noise reduction filter was applied, the recognition rate was lower than those reported in previous studies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Von Ahn, L., Blum, M., Langford, J.: Telling humans and computers apart automatically. Commun. ACM 47(2), 56–60 (2004)
Sivakorn, S., Polakis, J., Keromytis, A.D.: I’m not a human: breaking the google reCAPTCHA. Black Hat 14, 1–12 (2016)
Toru, H., Takashi, S.: Fooling Images Recognition by Many Discontinuous Points and Its Application to CAPTCHA. Inform. Process. Soc. Jpn. 60(12), 2139–2146 (2019) (in Japanese)
Color assimilation grid illusion. https://www.patreon.com/posts/color-grid-2873-4535. Accessed 28 Jan 2023
Vision AI cloud vision API google cloud. https://cloud.google.com/vision?hl=ja. Accessed 28 Jan 2023
General-image-recognition — Clarifai Community. https://clarifai.com/clarifai/main/models/general-image-recognition?inputId=C5yYr. Accessed 28 Jan 2023
Google image search. https://www.google.co.jp/imghp?hl=ja &tab=ri &ogbl. Accessed 28 Jan 2023
CLIP: connecting text and images. https://openai.com/blog/clip/. Accessed 28 Jan 2023
Acknowledgments
This work was supported by JSPS KAKENHI Grant Numbers JP21K11849, JP22K12013, and JP20K11812.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Nishikawa, S. et al. (2024). Study of an Image-Based CAPTCHA that is Resistant to Attacks Using Image Recognition Systems. In: Pan, JS., Pan, Z., Hu, P., Lin, J.CW. (eds) Genetic and Evolutionary Computing. ICGEC 2023. Lecture Notes in Electrical Engineering, vol 1114. Springer, Singapore. https://doi.org/10.1007/978-981-99-9412-0_19
Download citation
DOI: https://doi.org/10.1007/978-981-99-9412-0_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-9411-3
Online ISBN: 978-981-99-9412-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)