Current CAPTCHA Research Articles

Recent advances of Captcha security analysis: a short literature review

CAPTCHA has long been used to keep bots from misusing web services. Various CAPTCHA schemes have been proposed over the years, principally to increase usability and security against emerging bots and hackers performing malicious operations. However, automated attacks have effectively cracked all common conventional schemes, and the majority of present CAPTCHA methods are also vulnerable to human-assisted relay attacks. Invisible reCAPTCHA and some approaches have not yet been cracked. However, with the introduction of fourth generation bots accurately mimicking human behavior, a secure CAPTCHA would be hardly designed without additional special devices. In this paper, we presented a short literature review of the current CAPTCHA schemes, as well as highlighting new trends and open issues, the challenges, and the opportunities as a solid starting point for designing the future secure and usable CAPTCHA schemes.

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.

Scanning-to-speech challenge-response authentication test for visually impaired

Completely Automated Public Turing Tests to Tell Computer and Humans Apart (CAPTCHA) is an approach used to distinguish between a self-active computer program and a human. This kind of CAPTCHA is used in the field of computing to discover a particular user interacting with the system is human or not. It requires someone to enter the correct sequence of digits, characters, or both the combinations. The average time taken to solve the current captcha displayed will take around 10 s approximately. Research findings also discover additionally that the numerous famous CAPTCHA procedures are not powerful or secure, further entangling the test of offering services acquired from robotic intervention yet available to individuals with disabilities. This leads to the formulation of new approaches like QR Code Scanning-to-Speech, Revamping, and Randomness. This technique is encrypted end-to-end by using Blowfish Fermat Little Theorem (BFLT). There are a total of 156 physical users (both visually impaired and visually fit) were analyzed to assess the potency of the proposed approach. Further, it is compared with the current highest development CAPTCHA to test the performance of the QR Code Scanning-to-Speech, Revamping, and Randomness. The security scrutiny proved that the proposed approach is robust and hindering Hidden Markov Model (HMM), Fuzzy solver, and recent eminent attacks.

Proposal and evaluation for color constancy CAPTCHA

CAPTCHAs are technologies that distinguish humans and bot to prevent illegal access. Unfortunately, current CAPTCHAs, even the latest Google reCAPTCHA, have already broken with high accuracy. Although the devices, including emphasizing the distortion of the text and adding noise to the image, improve the machine resistance, they may decrease the accessibility of the web page. The purpose of this study is to propose a new CAPTCHA that can decrease the machine resistance while keeping usability. To achieve this purpose, we focused on color constancy. Color constancy is a human’s characteristic that enables humans to recognize the original color of the object by ignoring the effects of illumination light. Color constancy has not been fully reproduced by the program yet. We proposed color constancy CAPTCHA that the user is required to answer an original color of the object in a specified area on the CAPTCHA image with a color filter. In this paper, we created a prototype of CAPTCHA, applied two kinds of color filters, and then evaluated each case for the human success rate, machine success rate, and usability.

A survey of CAPTCHA technologies to distinguish between human and computer

CAPTCHA, Completely Automated Public Turing test to tell Computers and Humans Apart, is widely used as a security mechanism to classify human and computer. This security mechanism is based on the Turing Test, which has been conceived to ensure network security. Usability is another fundamental issue, which can avoid human users proceeding tedious and time-consuming operation. CAPTCHA design should consider security and usability simultaneously. This paper provides a review on the development of CAPTCHA technologies for human and computer classification, along with their applications and instantiations. Different from previous CAPTCHA survey, this review discusses the CAPTCHA mechanism from usability and security aspects, therefore attacking (anti-classification) and defending (classification) technologies towards current CAPTCHA are both reviewed. Besides, recent emerging CAPTCHA and the attacking techniques are also introduced in this paper, such as game CAPTCHA, deep learning-based attacking, and etc.

Modernization of CAPTCHA using Skin Detection Sensors: A Survey

CAPTCHA is a mechanism to protect the website from malicious programs called bots. The ability of humans to discern distorted characters and to correctly feed them into the computer distinguishes them from bots. With advent in artificial intelligence, the current CAPTCHA mechanisms have developed various flaws. This paper elaborates on the various CAPTCHA mechanisms, their flaws and proposes an alternative technique that uses skin detection to verify human presence.

A survey and analysis of current CAPTCHA approaches

Computer programs are misusing Internet services designed for humans. A CAPTCHA, Completely Automated Public Turing test to tell Computers and Humans Apart, is a standard security mechanism to defe...

CaptchAll: An Improvement on the Modern Text-based CAPTCHA

Current CAPTCHA implementations are a source of frustration for many and yet they are an integral and necessary piece of the World Wide Web, as we know it. This paper intends to propose a solution to this ever-growing problem, CaptchAll, an easy to use and difficult to break image-based CAPTCHA. In this system, image scenes of a complex nature are presented to the user along with a piece of challenge text, asking the user to identify objects in the image with a simple click. While this task is unproblematic for the typical Internet user, it is an incredibly challenging image processing task for an automated program without proper context. Initial in-depth analysis is able to demonstrate the user-friendly nature of the system while outlining the struggle in which automated attackers will face

EVALUATING A SEGMENTATION-RESISTANT CAPTCHA INSPIRED BY THE HUMAN VISUAL SYSTEM MODEL

Visual CAPTCHAs are widely used these days on the Internet as a means of distinguishing between humans and computers. They help protect servers from being flooded by requests from malicious scripts. However, they are not very secure. Numerous image processing algorithms are able to discern the characters used in the CAPTCHAs. It has been suggested that CAPTCHAs can be made more secure if they are distorted in ways that makes segmentation difficult. However, out of all the reviewed distortions present in current CAPTCHAs there are none that allow for a high level of segmentation difficulty. Furthermore, CAPTCHAs also need to be used by humans who may not find certain distortions tolerable. Thus, the problem of selecting a good distortion becomes a tradeoff between user acceptability and computer solvability. It is hypothesized in this paper that rather than use low-level image distortions, optical distortions based on the Gestalt laws of perception that govern human visual system models should be applied. These distortions would ensure widespread user acceptability (as they are based on the internal workings of the HVS), and be very difficult for computers to solve (as HVS perception models have been difficult to implement in computers). This paper aims to explore the feasibility of employing Gestalt-inspired distortion in CAPTCHAs by first implementing a CAPTCHA cracker and then evaluating the performance of some manually generated Gestalt CAPTCHA’s against some existing CAPTCHAs.