TY - GEN
T1 - Improvement of Text CAPTCHA Codes by Comparing Adversarial Techniques Against Deep Learning Model Attacks
AU - Montenegro, Luciana Vasquez
AU - Garcia, Giancarlo Lopez
AU - Cardenas, Edwin Jonathan Escobedo
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - CAPTCHAs are essential tools in computer security to distinguish between humans and automated programs. Although widely used in web applications to prevent unauthorized access and spam, advances in artificial intelligence have increased attacks against these systems. This study focuses on improving the security of CAPTCHAs using adversarial techniques such as FGSM and PGD, exploring their effectiveness against a deep learning model. Furthermore, a generative adversarial network is employed to strengthen resistance to these attacks. The research also includes human validation to evaluate the robustness of different types of CAPTCHAs against simulated attacks. Our findings demonstrate that while adversarial modifications enhance security, they require careful calibration to avoid excessive usability degradation.
AB - CAPTCHAs are essential tools in computer security to distinguish between humans and automated programs. Although widely used in web applications to prevent unauthorized access and spam, advances in artificial intelligence have increased attacks against these systems. This study focuses on improving the security of CAPTCHAs using adversarial techniques such as FGSM and PGD, exploring their effectiveness against a deep learning model. Furthermore, a generative adversarial network is employed to strengthen resistance to these attacks. The research also includes human validation to evaluate the robustness of different types of CAPTCHAs against simulated attacks. Our findings demonstrate that while adversarial modifications enhance security, they require careful calibration to avoid excessive usability degradation.
UR - https://www.scopus.com/pages/publications/105018911838
U2 - 10.1007/978-3-031-97913-2_11
DO - 10.1007/978-3-031-97913-2_11
M3 - Articulo (Contribución a conferencia)
AN - SCOPUS:105018911838
SN - 9783031979125
T3 - Communications in Computer and Information Science
SP - 133
EP - 144
BT - Artificial Intelligence, COMIA 2025 - 17th Mexican Congress, Proceedings
A2 - Martínez-Villaseñor, Lourdes
A2 - Martínez-Seis, Bella
A2 - Pichardo, Obdulia
PB - Springer Science and Business Media Deutschland GmbH
T2 - 17th Mexican Conference on Artificial Intelligence, COMIA 2025
Y2 - 12 May 2025 through 16 May 2025
ER -