Filters








516 Hits in 3.6 sec

Enhancing the Security of Image CAPTCHAs Through Noise Addition [chapter]

David Lorenzi, Emre Uzun, Jaideep Vaidya, Shamik Sural, Vijayalakshmi Atluri
2015 IFIP Advances in Information and Communication Technology  
In this paper, we present a generalized methodology to transform existing images by applying various noise generation algorithms into variants that are resilient to such attacks.  ...  Image CAPTCHAs provide an alternative that is often preferred to text-based implementations. However, Image CAPTCHAs have their own set of security and usability problems.  ...  Through this transformation, image CAPTCHAs can again become a viable alternative to text based CAPTCHAs having a similar level of security while providing a superior level of usability.  ... 
doi:10.1007/978-3-319-18467-8_24 fatcat:pcoz65gqyvgvddrf4lfwvg3knu

Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence [article]

Ning Zhang, Mohammadreza Ebrahimi, Weifeng Li, Hsinchun Chen
2022 arXiv   pre-print
In the dark web, CAPTCHA images are meticulously designed with additional background noise and variable character length to prevent automated CAPTCHA breaking.  ...  To eliminate the need for human involvement, the proposed framework utilizes Generative Adversarial Network (GAN) to counteract dark web background noise and leverages an enhanced character segmentation  ...  Background security measures provide additional obfuscation to the background of the CAPTCHA image by introducing dot noise (i.e., dot-shaped noise applied to the background surface while interfering with  ... 
arXiv:2201.02799v2 fatcat:nepnavt6onaf7ncinm2x6ar5ey

Automated CAPTCHA Solving: An Empirical Comparison of Selected Techniques

Michalis Korakakis, Emmanouil Magkos, Phivos Mylonas
2014 2014 9th International Workshop on Semantic and Social Media Adaptation and Personalization  
For each technique, we build a CAPTCHA solver and give it specific sets of text-based challenges to break.  ...  CAPTCHAs exploit the gap in the ability between a human and a machine to understand the semantics of specific multimedia content, with vast applications in computer security.  ...  Basis for Comparison The images used for the comparison were created by the ASP.NET Security Image Generator, a CAPTCHA-generating library freely available on the Web 1 .  ... 
doi:10.1109/smap.2014.29 dblp:conf/smap/KorakakisMM14 fatcat:jff7iipjfbaqzjz6lmimbbdsw4

Web security through improvised image based CAPTCHA

R. Murugan, Tejasri. P, Nobesh Reddy, G. Dinesh
2017 International Journal of Engineering & Technology  
Sometimes a human generated computer bot also known as Zombie may try to access the website.  ...  Initially CAPTCHA was developed on text-based platform later it was evolved to audio, image etc. In this paper a new technique to differentiate bots from humans is introduced.  ...  It is image of distorted text/numbers and addition to with some background noise or clutter. The content is generated randomly either text or alphanumeric.  ... 
doi:10.14419/ijet.v7i1.1.9481 fatcat:gvpemiswergmvdoael6qb2frsy

Robust CAPTCHA Image Generation Enhanced with Adversarial Example Methods

Hyun KWON, Hyunsoo YOON, Ki-Woong PARK
2020 IEICE transactions on information and systems  
The experimental results show that the CAPTCHA image generated via FGSM, I-FGSM, and DeepFool methods exhibits a 0% recognition rate with = 0.15 for FGSM, a 0% recognition rate with α = 0.1 with 50 iterations  ...  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.  ...  In addition, future research should focus on studying the generation of multiple CAPTCHA images by applying methods such as the generative adversarial network [11] .  ... 
doi:10.1587/transinf.2019edl8194 fatcat:i7upkzzdtndcbe5z4a3kztcu5a

Augmented Data Selector to Initiate Text-Based CAPTCHA Attack

Aolin Che, Yalin Liu, Hong Xiao, Hao Wang, Ke Zhang, Hong-Ning Dai, Ting Chen
2021 Security and Communication Networks  
Meanwhile, the data augmentor uses four different image noises to generate different CAPTCHA images.  ...  In the past decades, due to the low design cost and easy maintenance, text-based CAPTCHAs have been extensively used in constructing security mechanisms for user authentications.  ...  Finally, we add the noise matrix to the matrix of the normal text-based CAPTCHA to generate a Gaussian noise image. e function of Gaussian noise can be expressed as G � I + N g , (1) where G denotes the  ... 
doi:10.1155/2021/9930608 fatcat:lagesev6xzg2vmeddtz6ccjomy

Securing IoT Devices: A Robust and Efficient Deep Learning with a Mixed Batch Adversarial Generation Process for CAPTCHA Security Verification

Stephen Dankwa, Lu Yang
2021 Electronics  
The goal of this current study is to perform security vulnerability verification on adversarial text-based CAPTCHA, based on attacker–defender scenarios.  ...  An adversarial machine learning attack is a good practice to adopt, to strengthen the security of text-based CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart), to withstand  ...  Acknowledgments: First of all, the authors thank God for His strength and wisdom. The authors express their sincere thanks to Gao Bin for his advice.  ... 
doi:10.3390/electronics10151798 fatcat:e4khz6abfvglteflhgnvzwrbiy

CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks

Hyun Kwon, Hyunsoo Yoon, Ki-Woong Park
2020 Sensors  
In this work, we propose a method for generating a CAPTCHA image that will resist recognition by machines while maintaining its recognizability to humans.  ...  To prevent such automated attacks, CAPTCHAs are widely used as a security solution.  ...  In addition, it can be seen that the newly generated CAPTCHA images remain recognizable to humans.  ... 
doi:10.3390/s20051495 pmid:32182829 fatcat:u24ahe5kovh33alyuc5gihnss4

Survey on Captcha and its Techniques for BOT Protection

V. Premanand, A. Meiappane, V.Arulalan V.Arulalan
2015 International Journal of Computer Applications  
Generally the humans can perform this task well but the bots can"t resulting in highly secured system.  ...  The commonly used CAPTCHA are Visual CAPTCHA where the text (or) image is been muddled by changing the visual by the addition of some irregular fluctuations and distortion.  ... 
doi:10.5120/19181-0661 fatcat:4dvev2hfybebjipzcvfgbaz4wa

Design of Secure Multilingual CAPTCHA Challenge

M. Tariq Banday, Shafiya Afzal Sheikh
2015 International Journal of Web Portals  
The results of experiments, security tests, and users study with the CAPTCHA tests generated through the proposed technique have validated its design, security, usability, and accessibility.  ...  It discusses the design, algorithm, pseudo code, and working of a secure multilingual text CAPTCHA script having desired security, accessibility and usability features.  ...  To make these challenges difficult for bots to break, security of CAPTCHA tests were enhanced by adding deformation, distortion, random image backgrounds, noise, etc.  ... 
doi:10.4018/ijwp.2015010101 fatcat:5m3rv4p47bbbvikjqrqmkmjyaq

Gotta CAPTCHA 'Em All: A Survey of Twenty years of the Human-or-Computer Dilemma [article]

Meriem Guerar, Luca Verderame, Mauro Migliardi, Francesco Palmieri, Alessio Merlo
2021 arXiv   pre-print
Finally, an assessment of the open issues, challenges, and opportunities for further study is provided, paving the road toward the design of the next-generation secure and user-friendly CAPTCHA schemes  ...  In addition, for each identified CAPTCHA category, the most successful attack methods are summarized by also describing how CAPTCHA schemes evolved to resist bot attacks, and discussing the limitations  ...  for further study, drawing a roadmap for the design of the next generation of secure and user-friendly CAPTCHA schemes.  ... 
arXiv:2103.01748v1 fatcat:ufrqkfxyjrgwlmkwg7qlddpbou

A Survey and Analysis of Current CAPTCHA Approaches

Narges Roshanbin, James Miller
2013 Journal of Web Engineering  
Therefore, security researchers have become motivated to discover techniques to improve CAPTCHAs.  ...  Two fundamental issues with CAPTCHAs are usability and robustness. It is important for a CAPTCHA to be both legible for humans and strong against malicious computer programs.  ...  This CAPTCHA is convenient for users. In addition, since the required processing time in this CAPTCHA is relatively high, it is more secure.  ... 
dblp:journals/jwe/RoshanbinM13 fatcat:xy5pvkvnb5calkqu6ythkqiljy

A FRAMEWORK FOR DEVANAGARI SCRIPT-BASED CAPTCHA

Sushma Yalamanchili, Kameswara Rao
2011 Zenodo  
There is potential for an exponential rise in the applications that are likely to be developed in that script thereby making it easy to secure Indian language based applications.  ...  The design and implementation of CAPTCHAs fall in the realm of Artificial Intelligence. We aim to utilize CAPTCHAs as a tool to improve the security of Internet based applications.  ...  with additive background noise.  ... 
doi:10.5281/zenodo.3366494 fatcat:z74e2x4axnggraautwezp42rb4

A Framework for Devanagari Script-based Captcha [article]

Sushma Yalamanchili, M.Kameswara Rao
2011 arXiv   pre-print
There is potential for an exponential rise in the applications that are likely to be developed in that script thereby making it easy to secure Indian language based applications.  ...  The design and implementation of CAPTCHAs fall in the realm of Artificial Intelligence. We aim to utilize CAPTCHAs as a tool to improve the security of Internet based applications.  ...  with additive background noise.  ... 
arXiv:1109.0132v1 fatcat:6ar7g4pou5e3bktjbvlkdb72qi

HMM-based Attacks on Google's ReCAPTCHA with Continuous Visual and Audio Symbols

Shotaro Sano, Takuma Otsuka, Katsutoshi Itoyama, Hiroshi G. Okuno
2015 Journal of Information Processing  
CAPTCHAs distinguish humans from automated programs by presenting questions that are easy for humans but difficult for computers, e.g., recognition of visual characters or audio utterances.  ...  The state of the art research suggests that the security of visual and audio CAPTCHAs mainly lies in anti-segmentation techniques, because individual symbol recognition after segmentation can be solved  ...  We demonstrated how our framework was applied for actual CAPTCHA breakers targeting the current version of Google's re-CAPTCHA for both the visual and audio versions.  ... 
doi:10.2197/ipsjjip.23.814 fatcat:5r3gr7n5v5f3dje2vfbrinwsmu
« Previous Showing results 1 — 15 out of 516 results