278 Hits in 4.5 sec

Using Generative Adversarial Networks to Break and Protect Text Captchas

Guixin Ye, Zhanyong Tang, Dingyi Fang, Zhanxing Zhu, Yansong Feng, Pengfei Xu, Xiaojiang Chen, Jungong Han, Zheng Wang
2020 ACM Transactions on Privacy and Security  
This article presents a novel genetic text captcha solver based on the generative adversarial network.  ...  It then improves and ine-tunes the base solver using a small number of labeled real captchas.  ...  We show that our approach is robust and generally applicable, which can break many advanced security features used by modern text captchas.  ... 
doi:10.1145/3378446 fatcat:s3zvf3rlz5fzxnvnke645khm6y

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  
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  ...  Therefore, this study proposed computation-efficient deep learning with a mixed batch adversarial generation process model, which attempted to break the transferability attack, and mitigate the problem  ...  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

Adversarial CAPTCHAs [article]

Chenghui Shi, Xiaogang Xu, Shouling Ji, Kai Bu, Jianhai Chen, Raheem Beyah, Ting Wang
2019 arXiv   pre-print
Then, we propose a framework for text-based and image-based adversarial CAPTCHA generation on top of state-of-the-art adversarial image generation techniques.  ...  generation methods, and 8 new adversarial CAPTCHA generation methods.  ...  Then, following the design principle and goals, a straightforward idea is to generate text-based adversarial CAPTCHAs using exiting adversarial image generation techniques.  ... 
arXiv:1901.01107v1 fatcat:la4pc6q2t5cfzljvxogn53suge

An End-to-End Attack on Text-based CAPTCHAs Based on Cycle-Consistent Generative Adversarial Network [article]

Chunhui Li, Xingshu Chen, Haizhou Wang, Yu Zhang, Peiming Wang
2020 arXiv   pre-print
In this paper, we propose an efficient and simple end-to-end attack method based on cycle-consistent generative adversarial networks.  ...  As a widely deployed security scheme, text-based CAPTCHAs have become more and more difficult to resist machine learning-based attacks.  ...  The authors thank anonymous reviewers for their helpful comments to improve the paper.  ... 
arXiv:2008.11603v1 fatcat:5b5kw3in25dlpg44nphwa2ghyu

A Password-based Authentication System based on The CAPTCHA AI Problem

Masoud Alajmi, Ibrahim Elashry, Hala S. El-Sayed, Osama S. Faragallah
2020 IEEE Access  
In this system, a server sends a challenge text to a client, then the client generates a random image and blends the challenge text inside this random image using his password.  ...  Then the client sends the generated image to the server. The server extracts the challenge text from the sent image using his copy of the client's password.  ...  C tosses a fair coin b ∈ [0, 1] and uses CT ext b as the challenge text. Using CT ext b , S * , S * 1 and S * 2 , the challenger C generates the challenge image and sends it to the adversary A.  ... 
doi:10.1109/access.2020.3018659 fatcat:ize77xhfhndotbc5xeakyjpnfy

A Low-Cost Attack against the hCaptcha System [article]

Md Imran Hossen, Xiali Hei
2021 arXiv   pre-print
CAPTCHAs are a defense mechanism to prevent malicious bot programs from abusing websites on the Internet. hCaptcha is a relatively new but emerging image CAPTCHA service.  ...  This paper presents an automated system that can break hCaptcha challenges with a high success rate.  ...  This work is supported in part by US NSF under grant OIA-1946231.  ... 
arXiv:2104.04683v1 fatcat:5sdd4vlmjnhuhj6yudl6uenfny

An Object Detection based Solver for Google's Image reCAPTCHA v2 [article]

Md Imran Hossen, Yazhou Tu, Md Fazle Rabby, Md Nazmul Islam, Hui Cao, Xiali Hei
2021 arXiv   pre-print
We propose a fully automated object detection based system that breaks the most advanced challenges of reCAPTCHA v2 with an online success rate of 83.25%, the highest success rate to date, and it takes  ...  only 19.93 seconds (including network delays) on average to crack a challenge.  ...  We also want to thank our shepherd Kevin Borgolte and the anonymous reviewers for valuable comments.  ... 
arXiv:2104.03366v1 fatcat:i7jqvbcw5jdpplkmvz6ogcpfoy

Attacks as Defenses: Designing Robust Audio CAPTCHAs Using Attacks on Automatic Speech Recognition Systems [article]

Hadi Abdullah, Aditya Karlekar, Saurabh Prasad, Muhammad Sajidur Rahman, Logan Blue, Luke A. Bauer, Vincent Bindschaedler, Patrick Traynor
2022 arXiv   pre-print
using the differences between the ways that humans and computers process audio.  ...  Audio CAPTCHAs are supposed to provide a strong defense for online resources; however, advances in speech-to-text mechanisms have rendered these defenses ineffective.  ...  Using an adversarial example attack to generate CAPTCHAs has been previously proposed for text and image CAPTCHAs [60, 65, 84] .  ... 
arXiv:2203.05408v1 fatcat:v5eo4d2e7javfnsllboxygoh5q

CAPTCHA-based Code Voting

Rolf Oppliger, Jörg Schwenk, Christoph Löhr
2008 International Conference on Electronic Voting  
In this paper,w e propose the use of CAPTCHA-an acronym standing for Completely Automated Public Turing tests to tell Computers and Humans Apartto improve the user-friendliness of code voting, discuss  ...  the security of CAPTCHAbased code voting, and elaborate on a possible implementation.  ...  Alternatively speaking, if an adversary is able to break the CAPTCHAs in use, then he is also able to break the security of CAPTCHAbased code voting.  ... 
dblp:conf/ev/OppligerSL08 fatcat:fnub3h56trgafm2lx74apkyky4

Capture the Bot: Using Adversarial Examples to Improve CAPTCHA Robustness to Bot Attacks [article]

Dorjan Hitaj, Briland Hitaj, Sushil Jajodia, Luigi V. Mancini
2020 arXiv   pre-print
While typically adversarial examples are used to lead an ML model astray, with CAPTURE, we attempt to make a "good use" of such mechanisms.  ...  In this work, we take the first step to address this problem. We introduce CAPTURE, a novel CAPTCHA scheme based on adversarial examples.  ...  We identify two similar techniques to generate unconstrained adversarial examples and show how they can be used individually to build a strong CAPTCHA.  ... 
arXiv:2010.16204v2 fatcat:cukulgj5ivbijlfuixwkjvwlma

No Bot Expects the DeepCAPTCHA! Introducing Immutable Adversarial Examples, With Applications to CAPTCHA Generation

Margarita Osadchy, Julio Hernandez-Castro, Stuart Gibson, Orr Dunkelman, Daniel Perez-Cabo
2017 IEEE Transactions on Information Forensics and Security  
Recent advances in Deep Learning (DL) allow for solving complex AI problems that used to be considered very hard.  ...  ACKNOWLEDGEMENTS The authors thank Daniel Osadchy for his worthy contributions to the paper and the anonymous reviewers for their ideas and suggestions.  ...  This research was supported by UK Engineering and Physical Sciences Research Council project EP/M013375/1 and by the Israeli Ministry of Science and Technology project 3-11858.  ... 
doi:10.1109/tifs.2017.2718479 fatcat:t2e5kcddcbaezb6bswdtqfeweq

Simple and Easy: Transfer Learning-Based Attacks to Text CAPTCHA

Ping Wang, Haichang Gao, Ziyu Shi, Zhongni Yuan, Jiangping Hu
2020 IEEE Access  
CAPTCHA, or Completely Automated Public Turing Tests to Tell Computers and Humans Apart, is a common mechanism used to protect commercial accounts from malicious computer bots, and the most widely used  ...  To further explore the effect of the training sample characteristics on the attack accuracy, we elaborately imitate some samples and apply a generative adversarial network to refine the samples, sequentially  ...  Due to the difficulty of collecting and manually labeling real CAPTCHAs, it has become a trend to use synthetic samples to break text-based CAPTCHA. In 2015, Stark et al.  ... 
doi:10.1109/access.2020.2982945 fatcat:2di2z5vggrb3pojg7dm7daqfe4

Against Spyware Using CAPTCHA in Graphical Password Scheme

Liming Wang, Xiuling Chang, Zhongjie Ren, Haichang Gao, Xiyang Liu, Uwe Aickelin
2010 2010 24th IEEE International Conference on Advanced Information Networking and Applications  
We propose a new scheme, using CAPTCHA (Completely Automated Public Turing tests to tell Computers and Humans Apart) that retaining the advantages of graphical password schemes, while simultaneously raising  ...  Text-based password schemes have inherent security and usability problems, leading to the development of graphical password schemes.  ...  ACKNOWLEDGMENT The authors would like to thank the reviewers for their careful reading of this paper and for their helpful and constructive comments.  ... 
doi:10.1109/aina.2010.46 dblp:conf/aina/WangCRGLA10 fatcat:6umk64cc7zbkffvkp5uefubo3e

Designing Proof of Human-Work Puzzles for Cryptocurrency and Beyond [chapter]

Jeremiah Blocki, Hong-Sheng Zhou
2016 Lecture Notes in Computer Science  
By contrast, CAPTCHAs are only difficult for other computers to solve -not for the computer that generated the puzzle.  ...  We show how to construct PoH puzzles from indistinguishability obfuscation and from CAPTCHAs. We motivate our ideas with two applications: HumanCoin and passwords.  ...  Acknowledgments: The authors thank paper shepherd Peter Gaži for his very constructive feedback which helped us to improve the quality of the paper.  ... 
doi:10.1007/978-3-662-53644-5_20 fatcat:m4wa3kkx6naglmtriqqbzjypk4

Captcha Attack: Turning Captchas Against Humanity [article]

Mauro Conti, Luca Pajola, Pier Paolo Tricomi
2022 arXiv   pre-print
In this work, we propose CAPtcha Attack (CAPA), an adversarial technique that allows users to spread inappropriate text online by evading ACM controls.  ...  Nowadays, people generate and share massive content on online platforms (e.g., social networks, blogs).  ...  The research community put much effort into solving (or breaking) text-based captchas (the type used in our attack).  ... 
arXiv:2201.04014v3 fatcat:4yo7gcznhfgtnf5m324hxnjbri
« Previous Showing results 1 — 15 out of 278 results