Text-based CAPTCHA Research Articles

A Review on CAPTCHAs in Use with Focus on Their Existing Vulnerabilities Concerning Web Security

Over last decades or so, CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart)are used to differentiate between humans and bots. In spite of the fact that numerous choices of CAPTCHAs are presented in later a long time but still text-based CAPTCHAs are most predominant among all other choices on the web. CAPTCHA has been broadly utilized over web to guard against assaults from pernicious bots and robotized assaults.Hackers use bots which perform auto registrations on the websites, often resulting in wastage of resources and compromising the security of the website. Therefore, we need a web security component like CAPTCHA which helps us in telling human clients separated from computerprograms. With progresses in Artificial Intelligence and computer vision, it is currently conceivable to break the current CAPTCHAs.InText-based CAPTCHA,more distortion, different orientation and noise make it difficult for humans also. Text-based Captcha can be cracked by using OCR software.It is suffered by relay, random guess, and dictionary attacks. In images-based captcha, sometimes it very difficult to read and are not compatible with users with disabilities. It is also time-consuming to decipher with technical difficulties with certain internet browsers. It may greatly enhance Artificial Intelligence. In audio based CAPTCHA, performance of human users on this task is highly dependent on their fluency. This implies more youthful users whose language abilities are not all around created, non-local speakers or clients with language or learning incapacities may not perform well. In this research work, various reviews of the existing CAPTCHAs in use, with major focus on their existing vulnerabilities has been performed.

Semi-supervised deep learning approach to break common CAPTCHAs

Manual data annotation is a time consuming activity. A novel strategy for automatic training of the CAPTCHA breaking system with no manual dataset creation is presented in this paper. We demonstrate the feasibility of the attack against a text-based CAPTCHA scheme utilizing similar network infrastructure used for Denial of Service attacks. The main goal of our research is to present a possible vulnerability in CAPTCHA systems when combining the brute-force attack with transfer learning. The classification step utilizes a simple convolutional neural network with 15 layers. Training stage uses automatically prepared dataset created without any human intervention and transfer learning for fine-tuning the deep neural network classifier. The designed system for breaking text-based CAPTCHAs achieved 80% classification accuracy after 6 fine-tuning steps for a 5 digit text-based CAPTCHA system. The results presented in this paper suggest, that even the simple attack with a large number of attacking computers can be an effective alternative to current CAPTCHA breaking systems.

Position-Encoding Convolutional Network to Solving Connected Text Captcha

Abstract Text-based CAPTCHA is a convenient and effective safety mechanism that has been widely deployed across websites. The efficient end-to-end models of scene text recognition consisting of CNN and attention-based RNN show limited performance in solving text-based CAPTCHAs. In contrast with the street view image and document, the character sequence in CAPTCHA is non-semantic. The RNN loses its ability to learn the semantic context and only implicitly encodes the relative position of extracted features. Meanwhile, the security features, which prevent characters from segmentation and recognition, extensively increase the complexity of CAPTCHAs. The performance of this model is sensitive to different CAPTCHA schemes. In this paper, we analyze the properties of the text-based CAPTCHA and accordingly consider solving it as a highly position-relative character sequence recognition task. We propose a network named PosConv to leverage the position information in the character sequence without RNN. PosConv uses a novel padding strategy and modified convolution, explicitly encoding the relative position into the local features of characters. This mechanism of PosConv makes the extracted features from CAPTCHAs more informative and robust. We validate PosConv on six text-based CAPTCHA schemes, and it achieves state-of-the-art or competitive recognition accuracy with significantly fewer parameters and faster convergence speed.

Research on Deep Learning Techniques in Breaking Text-Based Captchas and Designing Image-Based Captcha

Optical character recognition (OCR) is a process of text recognition in images (one word). The input images are taken from the dataset. The collected text images are implemented to pre-processing. In pre-processing, we can implement the image resize process. Image resizing is necessary when you need to increase or decrease the total number of pixels, whereas remapping can occur when you are zooming refers to increase the quantity of pixels, so that when you zoom an image, you will see clear content. After that, we can implement the segmentation process. In segmentation, we can segment the each characters in one word. We can extract the features values from the image that means test feature. In classification process, we have to classify the text from the image. Image classification is performed the images in order to identify which image contains text. A classifier is used to identify the image containing text. The experimental results shows that the accuracy.

TICS: text–image-based semantic CAPTCHA synthesis via multi-condition adversarial learning

CAPTCHA is used to distinguish humans from automated programs and plays an important role in multimedia security mechanisms. Traditional CAPTCHA methods like image-based CAPTCHA and text-based CAPTCHA are usually based on word-level understanding, which can be easily cracked due to the recent success of deep learning techniques. To this end, this paper proposes a text–image-based CAPTCHA based on the cognition process and semantic reasoning and a novel model to generate the CAPTCHA. This method synthesizes three features: sentence, object, and location to generate a multi-conditional CAPTCHA that can resist the attack of the classification of CNN. A quantity of experiments has been conducted, and the result showed that the classification of ResNet-50 on the proposed TIC only achieves 3.38% accuracy.

Interactive Handwritten and Text-Based Handwritten Arabic CAPTCHA Schemes for Mobile Devices: A Comparative Study

CAPTCHA tests (Completely Automated Public Turing test to tell Computer and Humans Apart) are used by many services and websites. Recently, researchers have proposed interactive handwritten and text-based handwritten Arabic CAPTCHA schemes. The former scheme presents a handwritten CAPTCHA image, then requests users to select the joints between Arabic letters. In the latter scheme, a new generator of Arabic handwritten CAPTCHA images is developed, once the image is generated, the user is asked to type the letters shown in the image. Although both of them have shown promising results, this experimental study compares them in terms of security and usability for mobile device applications. The results demonstrated that the interactive scheme performs better than the text-based handwritten scheme in both usability and security.

CAPTCHA Recognition Using Deep Learning with Attached Binary Images

Websites can increase their security and prevent harmful Internet attacks by providing CAPTCHA verification for determining whether end-user is a human or a robot. Text-based CAPTCHA is the most common and designed to be easily recognized by humans and difficult to identify by machines or robots. However, with the dramatic advancements in deep learning, it becomes much easier to build convolutional neural network (CNN) models that can efficiently recognize text-based CAPTCHAs. In this study, we introduce an efficient CNN model that uses attached binary images to recognize CAPTCHAs. By making a specific number of copies of the input CAPTCHA image equal to the number of characters in that input CAPTCHA image and attaching distinct binary images to each copy, we build a new CNN model that can recognize CAPTCHAs effectively. The model has a simple structure and small storage size and does not require the segmentation of CAPTCHAs into individual characters. After training and testing the proposed CAPTCHA recognition CNN model, the achieved experimental results reveal the strength of the model in CAPTCHA character recognition.

A Novel Design of Audio CAPTCHA for Visually Impaired Users

CAPTCHAs are widely used by web applications for the purpose of security and privacy. However, traditional text-based CAPTCHAs are not suitable for sighted users much less users with visual impairments. To address the issue, this paper proposes a new mechanism for CAPTCHA called HearAct, which is a real-time audio-based CAPTCHA that enables easy access for users with visual impairments. The user listens to the sound of something (the “sound-maker”), and he/she must identify what the sound-maker is. After that, HearAct identifies a word and requires the user to analyze a word and determine whether it has the stated letter or not. If the word has the letter, the user must tap and if not, they swipe. This paper presents our HearAct pilot study conducted with thirteen blind users. The preliminary user study results suggest the new form of CAPTCHA has a lot of potential for both blind and visual users. The results also show that the HearAct CAPTCHA can be solved in a shorter time than the text-based CAPTCHAs because HearAct allows users to solve the CAPTCHA using gestures instead of typing. Thus, participants preferred HearAct over audio-based CAPTCHAs. The results of the study also show that the success rate of solving the HearAct CAPTCHA is 82.05% and 43.58% for audio CAPTCHA. A significant usability differences between the System Usability score for HearAct CAPTCHA method was 88.07 compared to audio CAPTCHA was 52.11%. Using gestures to solve the CAPTCHA challenge is the most preferable feature in the HearAct solution. To increase the security of HearAct, it is necessary to increase the number of sounds in the CAPTCHA. There is also a need to improve the CAPTCHA solution to cover wide range of users by adding corresponding image with each sound to meet deaf users’ needs; they then need to identify the spelling of the sound maker’s word.

Распознавание CAPTCHA на основе генеративно-состязательной сети

CAPTCHA recognition is certainly not a new research topic. Over the past decade, researchers have demonstrated various ways to automatically recognize text-based CAPTCHAs. However, in such methods, the recognition setup requires a large participation of experts and carries a laborious process of collecting and marking data. This article presents a general, low-cost, but effective approach to automatically solving text-based CAPTCHAs based on deep learning. This approach is based on the architecture of a generative-competitive network, which will significantly reduce the number of real required CAPTCHAs.

A Proposed Methodology for Detecting Human Attacks on Text-based CAPTCHAs

A Proposed Methodology for Detecting Human Attacks on Text-based CAPTCHAs

Using Generative Adversarial Networks to Break and Protect Text Captchas

Text-based CAPTCHAs remains a popular scheme for distinguishing between a legitimate human user and an automated program. This article presents a novel genetic text captcha solver based on the generative adversarial network. As a departure from prior text captcha solvers that require a labor-intensive and time-consuming process to construct, our scheme needs significantly fewer real captchas but yields better performance in solving captchas. Our approach works by first learning a synthesizer to automatically generate synthetic captchas to construct a base solver. It then improves and fine-tunes the base solver using a small number of labeled real captchas. As a result, our attack requires only a small set of manually labeled captchas, which reduces the cost of launching an attack on a captcha scheme. We evaluate our scheme by applying it to 33 captcha schemes, of which 11 are currently used by 32 of the top-50 popular websites. Experimental results demonstrate that our scheme significantly outperforms four prior captcha solvers and can solve captcha schemes where others fail. As a countermeasure, we propose to add imperceptible perturbations onto a captcha image. We demonstrate that our countermeasure can greatly reduce the success rate of the attack.

Efficient and secure flash-based gaming CAPTCHA

With the growth of connectivity to smart grids, new applications, and the changing interaction between customer and energy clouds, clouds are more vulnerable to denial-of-service attacks. Efficient detection methods are required to authenticate, detect and control attackers. Completely Automated Public Turing test to tell Computers and Humans Apart, CAPTCHA, is one efficient tool to thwart denial of service attacks. The server presents the user with a client puzzle to solve in order to gain access to the service or website. The puzzle should be hard enough for computers, but easy for humans to solve. Several methods have been suggested including the popular image-based, as well as video-based, and text-based CAPTCHAs. In this paper, we present a new Flash-based gaming CAPTCHA to differentiate bots from humans. We propose a drag and drop client puzzle where the user will play a simple game to answer a visual question. Our method turns out to be convenient, easy for users and challenging for bots. Additionally, it has gaming aspect, which makes it interesting to users of all age groups.

Deciphering complex text-based CAPTCHAs with deep learning

Background: CAPTCHA is a mechanism to distinguish humans from bots. It has become standard means of protection from the misuse of resources on World Wide Web. Different types of CAPTCHAs are implemented but text-based schemes are the most widely used due to its easiness and robustness. A user is asked to type in the text from an image. The image is intentionally distorted to dodge the bots. Recognizing the text is easy for humans but very hard for computers. Method/Findings: In this work, a text-based CAPTCHA scheme with background clutter and partially connected characters is decoded. The main steps consist on preprocessing, segmentation and recognition. Several digital image processing techniques were applied during preprocessing, segmentation steps and convolutional neural network (CNN) was used for recognition process. Since massive data is required for CNN therefore data was generated synthetically. A complex text-based CAPTCHA scheme with varying number of letters: 3, 4 and 5 letters is decoded with the overall precision of 77.5%, 64.2% and 51.9% respectively. Keywords: CAPTCHAs; HIPs; image processing; machine learning; CNN

Applying Visual Cryptography to Enhance Text Captchas

Nowadays, lots of applications and websites utilize text-based captchas to partially protect the authentication mechanism. However, in recent years, different ways have been exploited to automatically recognize text-based captchas especially deep learning-based ways, such as, convolutional neural network (CNN). Thus, we have to enhance the text captchas design. In this paper, using the features of the randomness for each encoding process in visual cryptography (VC) and the visual recognizability with naked human eyes, VC is applied to design and enhance text-based captcha. Experimental results using two typical deep learning-based attack models indicate the effectiveness of the designed method. By using our designed VC-enhanced text-based captcha (VCETC), the recognition rate is in some degree decreased.

DotCHA: An Interactive 3D Text-based CAPTCHA

We introduce a new type of 3D text-based CAPTCHA, called DotCHA, which relies on human interaction and overcomes the limitations of existing 2D and 3D CAPTCHAs. DotCHA asks users to rotate a 3D text model to identify the correct letters. The 3D text model is a twisted form of sequential 3D letters around a center pivot axis, and it shows different letters depending on the rotation angle. Because each model consists of many small spheres instead of a solid letter model, DotCHA is classified as a scatter-type CAPTCHA and resists character segmentation attacks. Moreover, DotCHA is resistant to machine learning attacks because each letter is only identified in a particular direction. We demonstrate that DotCHA is resistant to existing types of attacks while maintaining usability.

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

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 scheme is text-based CAPTCHA. In recent years, newly emerged deep learning techniques have achieved high accuracy and speed in attacking text-based CAPTCHAs. However, most of the existing attacks have various disadvantages, the attack process made high complexity or manually collecting and labeling a large number of samples to train a deep learning recognition model is time-consuming and expensive. In this paper, we propose a transfer learning-based approach that greatly reduces the attack complexity and the cost of labeling samples, specifically, by pre-training the model with randomly generated samples and fine-tuning the pre-trained model with a small number of real-world samples. To evaluate our attack, we tested 25 online CAPTCHAs achieving success rates ranging from 36.3% to 96.9%. 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 we use these two kinds of generated samples to pre-train the models, respectively. The experimental results demonstrate that the similarity between randomly generated samples and elaborately imitated samples has a negligible impact on the attack accuracy. Instead, transfer learning is the key factor; it reduces the cost of data preparation while preserving the model's attack accuracy.

Recognition of Text CAPTCHA by using Back Propagation Algorithm of Artificial Neural network

Text-based CAPTCHA is a very simple type of CAPTCHA which are most widely used. It uses only a group of characters. In this paper, we focus on how Text based CAPTCHA is recognized by machine learning techniques. This paper proposed a method based on Back Propagation algorithm to identify the Text based CAPTCHA. The proposed technique improves the security level of Text-based CAPTCHA storage system by using the Back-propagation method of Artificial Neural Network. We used NNToolbox to train the network in MATLAB software

An End-to-End Attack on Text CAPTCHAs

Text-based CAPTCHAs are the most widely used CAPTCHA scheme. Most text-based CAPTCHAs have been cracked. However, previous works have mostly relied on a series of preprocessing steps to attack text CAPTCHAs, which was complicated and inefficient. In this paper, we introduce a simple, generic, and effective end-to-end attack on text CAPTCHAs without any preprocessing. Through a convolutional neural network and an attention-based recurrent neural network, our attack broke a wide range of real-world text CAPTCHAs that are deployed by the top 50 most popular websites ranked by Alexa.com. In addition, this paper comprehensively analyzed the security of most resistance mechanisms of text-based CAPTCHAs through experiments. Experimental results prove that the anti-segmentation principle can be completely broken under deep learning attacks without any segmentation or preprocessing steps in contrast to commonly held beliefs.

Exploring the usability of the text-based CAPTCHA on tablet computers

This paper analyses and discusses the usability aspect of the text-based CAPTCHA in terms of response time and success in solving the CAPTCHA on tablet computers. The response time is the time spent by the user to find a solution to the CAPTCHA. The analysis is separately conducted on text-based CAPTCHA with only text and numbers. Then, the results are compared and the differences in response time and success in solving the two types of CAPTCHA are underlined. This is accomplished by asking 125 Internet users to solve the text-based CAPTCHA on the tablet computer. Their gender, age, education level, Internet experience, response time and success in solving two types of text-based CAPTCHA are collected in a dataset. Then, advanced statistical analysis by association rule mining is performed. It shows the dependence of the response time and success in solving the CAPTCHA on co-occurrence of gender, age, education level and Internet experience and the strength of this dependence by support, confidence and lift measures. This study provides relevant information for designing new CAPTCHAs which may be more accustomed to specific types of Internet users.

Evaluating and Designing a Secure Text-Based CAPTCHA and Picture Password for Online Examinations

International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.