35 results about "CAPTCHA" patented technology

According to one embodiment, a method, computer system, and computer program product for CAPTCHA image generation and verification is provided. The embodiment may include generating a first set of attributes. The embodiment may also include generating an image from the first set of attributes. The embodiment may further include generating a plurality of attribute options where the plurality of attribute options comprises at least one attribute within the first set of attributes. The embodiment may also include displaying the generated image with the plurality of generated attribute options. The embodiment may further include prompting a user to select the at least one attribute from the plurality of generated attributes depicted in the displayed image. The embodiment may also include receiving a user selection based on the prompt. The embodiment may further include, in response to the received user selection being correct, verifying the user is a human.

Systems and methods for generating a CAPTCHA challenge in a virtual environment are disclosed. The methods display a spatially anchored virtual 3D object in a virtual environment where certain features of the 3D object are hidden or occluded. The methods provide general, specific, or no instructions to a user for manipulating the displayed 3D virtual object. Upon determining that the manipulations performed follow the instructions, the occluded feature is revealed. Varying degrees of CAPTCHA challenges are provided that include moving real life objects, leveraging user background in generating customized CAPTCHA challenges, and camouflaging the virtual objects to make solving the CAPTCHA more challenging. The methods query the user to provide an input that reflects the revealed occluded feature, and, if the response to the query meets the predetermined response, access to the secured data requested in granted.

A system and method are disclosed for touchless, gesture-based form validation using real-time input from a standard camera. Spatial hand gestures are interpreted as mouse-like actions—such as drag, click, scroll, and hold—to complete form tasks without physical input. The system includes a vision-based input module, an AI-powered gesture recognition engine using landmark extraction, an interaction handler that maps gestures to DOM-compliant events, and a validation controller that confirms field focus, checkbox toggling, and submission. A visual feedback renderer provides real-time cues indicating gesture success, failure, or activity. Navigation buttons enable directional control and element repositioning. The method supports secure CAPTCHA-style workflows via randomized tasks and gesture thresholds, executing natively in browsers using WebAssembly or TensorFlow.js. Applications include bot prevention, accessible interaction, and secure, device-free input for web and mobile environments.

The present disclosure relates generally to computer-implemented systems and techniques for leveraging a virtual decentralized database to enable user identity authentication and verification of user activity and associated behaviors on open internet and public web-based and native applications. Techniques are disclosed for user identification profile onboarding using biometrics, frictionless CAPTCHA (Completely Automatic Public Turing Tests To Tell Humans And Computers Apart) processes, passive data capture of physiological and behaviors using device sensors, and cryptographic methods of storing user engagement activity as immutable data files for secure distribution on a decentralized virtual private network. Such technologies operate to establish a high confidence level for user authenticity, communication origin, engagement outcome transparency and clarity of intent for users active on social, commercial, e-commerce and information sharing platforms. More specifically, an unobtrusive passive data capture method of authentication and verification on a secure VPN supports the organic, spontaneous and original experience audiences desire while simultaneously eliminating opportunities for unscrupulous actors to exploit open internet exchanges by inserting fraudulent user accounts, automated bots and other measures that mimic or impersonate live humans, which ultimately undermines user confidence in data safety and erodes mutual trust between people, companies and institutions.

Claim 1: Captcha System A captcha system for verifying whether a website visitor is a human, comprising: • Server software that stores a large number of images and drawings, all of which have the same file size and format. • A function for randomly generating and storing values ​​that are assigned to each image, whereby these values ​​are not visible to the website visitor.

A computing platform may train, using historical call information, a prompt generation model to identify, for an initiated call between a first individual and a second individual, one or more security prompts to validate an identity of the first individual. The computing platform may detect and temporarily pause a call. The computing platform may input, into the prompt generation model, information of the call, which may cause the prompt generation model to output the security prompts, which may be customized CAPTCHA tests based on the information. The computing platform may send, while the call is paused and to a user device of the first individual, the security prompts. The computing platform may receive, while the call is paused and from the user device, responses to the one or more security prompts. The computing platform may validate, while the call is paused, the responses, and resume the call.

The present disclosure relates to image-based CAPTCHA challenges. Systems and methods of determining image features are provided. More specifically, a first image having unknown features can be obtained. The first image can be provided to a plurality of user devices in a verification challenge. The verification challenge can include one or more instructions to be presented to a user of each user device. The instructions are determined based at least in part on the first image. User responses can be received, and the unknown features of the first image can be determined based at least in part on the received responses. After the unknown features of the first image are determined, one or more machine learning models can be trained based at least in part on the determined features.

Methods and systems for generating completely automated public Turing test (CAPTCHA) images are provided. In some examples, a method includes generating a plurality of images using a generative imaging model, providing the plurality of images to a user with a description that corresponds to one of a similarity or difference between the plurality of images, receiving a selection of an image of the plurality of images, determining if the selection is correct based on the provided description, and outputting an indication of whether the selection is correct.

This invention discloses an intelligent CAPTCHA method. Its key feature is that when a webpage is opened, the SDK begins collecting browser parameters, mouse and keyboard events, and sends them to the server. By collecting and judging the user's browser parameters and behaviors, the results are fed back to the SDK. A prediction model is constructed and trained within an AI prediction model to assist in the human-machine verification of the CAPTCHA service. The prediction model comprehensively analyzes parameters such as the trajectory, direction, and speed of the user dragging the CAPTCHA slider to predict whether it is a human operation. This achieves accurate and efficient judgment of human-machine operation without the user's awareness, saving time and operational costs for normal users, and minimizing the impact on normal users by optimizing parameters.

The present application relates to the technical field of Internet, and more particularly to a slider verification code recognition method and system based on RPA and LBP features. The method comprises the following steps: S1, obtaining a slider gap picture and a background picture by using an RPA element screenshot component; S2, calculating the coordinate position of the slider gap on the background picture based on LBP features; S3, restoring the slider to the leftmost original position, and cracking the slider verification code according to the coordinate position of the slider gap on the background picture and the coordinate distance in the X-axis direction. The present application has the characteristics of being able to efficiently describe the texture of an image, being less affected by the brightness of the image, having higher robustness, small calculation amount, fast operation speed, and being more conducive to deployment.

Systems and methods for generating a CAPTCHA challenge in a virtual environment are disclosed. The methods display a spatially anchored virtual 3D object in a virtual environment where certain features of the 3D object are hidden or occluded. The methods provide general, specific, or no instructions to a user for manipulating the displayed 3D virtual object. Upon determining that the manipulations performed follow the instructions, the occluded feature is revealed. Varying degrees of CAPTCHA challenges are provided that include moving real life objects, leveraging user background in generating customized CAPTCHA challenges, and camouflaging the virtual objects to make solving the CAPTCHA more challenging. The methods query the user to provide an input that reflects the revealed occluded feature, and, if the response to the query meets the predetermined response, access to the secured data requested in granted.

This invention relates to the field of security verification technology, and discloses a verification method, device, storage medium, and apparatus based on CAPTCHA. The method includes: providing a fillable CAPTCHA corresponding to the service to be verified, wherein the fillable CAPTCHA includes an obstacle area and a region to be filled; obtaining the user's operation position based on the fillable CAPTCHA; filling the region to be filled according to the operation position and the obstacle area; and verifying the user based on the filling result. Because this invention proposes a fillable CAPTCHA and fills the CAPTCHA based on the user's click operation on the fillable CAPTCHA, and verifies the user based on the filling result, the complexity of the CAPTCHA can be increased, preventing the CAPTCHA from being cracked and improving security.

This invention discloses a method and device for image CAPTCHA verification processing using an AI large-scale model, relating to the field of computer network security technology. The method includes: detecting the execution of a specified operation and triggering a CAPTCHA generation request; based on the CAPTCHA generation request, invoking a pre-trained AI large-scale model and generating adaptive image CAPTCHA content in conjunction with current scene information; based on the generated image CAPTCHA content, acquiring user interaction operations and collecting interaction operation data; invoking the pre-trained AI large-scale model to perform multi-dimensional verification on the interaction operation data, including result correctness, operation behavior authenticity, and risk level assessment; and returning verification result information to the client based on the multi-dimensional verification results of the AI ​​large-scale model. This method has the advantages of improving CAPTCHA security and user experience, and achieving dynamic risk adaptation.

A user verification method and apparatus using CAPTCHA includes determining a correct answer pattern composed of at least one correct answer direction, generating an animation of an arrow object for each of the at least one correct answer direction, the arrow object rotating with a motion different from other directions related to the correct answer direction, displaying a CAPTCHA interface including an arrangement of the generated animations corresponding to the correct answer pattern, receiving a direction input from a user, and determining whether or not to verify the user according to a result of comparing the received direction input with the correct answer pattern.

Methods and systems for generating completely automated public Turing test (CAPTCHA) images are provided. In some examples, a method includes generating a plurality of images using a generative imaging model, providing the plurality of images to a user with a description that corresponds to one of a similarity or difference between the plurality of images, receiving a selection of an image of the plurality of images, determining if the selection is correct based on the provided description, and outputting an indication of whether the selection is correct.

A computing platform may train, using historical call information, a prompt generation model to identify, for an initiated call between a first individual and a second individual, one or more security prompts to validate an identity of the first individual. The computing platform may detect and temporarily pause a call. The computing platform may input, into the prompt generation model, information of the call, which may cause the prompt generation model to output the security prompts, which may be customized CAPTCHA tests based on the information. The computing platform may send, while the call is paused and to a user device of the first individual, the security prompts. The computing platform may receive, while the call is paused and from the user device, responses to the one or more security prompts. The computing platform may validate, while the call is paused, the responses, and resume the call.

The application discloses a Captcha recognition method and system based on an improved YOLO9000 algorithm, belongs to the technical field of Captcha recognition, and aims to solve the technical problem of how to quickly and accurately realize Captcha recognition. The method comprises the following steps: collecting Captcha pictures, wherein Captchas in the Captcha pictures are composed of Chinese characters, English and numbers; labeling Chinese characters in the Captchas and performing image transformation processing on the Captcha pictures; for a YOLO9000 model, the convolution of a bottleneck structure is reduced, the convolution layer is improved, a cross-entropy loss function and an average difference similarity function are used as a loss function, and a Captcha recognition model is constructed based on the improved YOLO9000 model; a Captcha recognition model is constructed based on a DBN model; the YOLO model and the DBN model are trained based on the preprocessed training samples; and the classification results are fused by adopting a linear credibility accumulation mode.

This disclosure provides an adaptive multimodal adversarial CAPTCHA image generation method and apparatus, comprising: obtaining the risk level of the current CAPTCHA image usage environment; determining the text perturbation intensity and image perturbation intensity required for CAPTCHA image generation based on the risk level; embedding implicit adversarial instructions into the natural language instruction text used for CAPTCHA image generation based on the text perturbation intensity to induce logical contradictions or illusions in the target model; the target model being a multimodal large model used to crack the CAPTCHA image; and inputting the natural language instruction text with embedded implicit adversarial instructions and the image perturbation intensity into a pre-trained latent space diffusion model, which then generates the CAPTCHA image. In this way, this disclosure effectively solves the problem that existing adversarial CAPTCHA images are easily neutralized by diffusion models, significantly improving the defense capability of adversarial CAPTCHA images against multimodal large model cracking behavior.

In view of the foregoing, a more effective and novel CAPTCHAs exhibit two features: first, it should explore other human-computer differences besides intelligence, as the intelligent gap between humans and computers is diminishing and second, the puzzle should stay with whoever requested it, such that it cannot be easily forwarded to a third-party such as a CAPTCHA farm. Systems and methods in accordance with various improved CAPTCHA approaches no longer rely on determining the intelligent differences between a human and a bot. Rather, the improved CAPTCHA approaches leverage physical differences between humans and bots.

The application discloses a kind of based on dynamic feature identification intelligent crawler safety collection method and system, including URL manager, dispatcher, resolver, downloader and data storage.Will be added and maintained to be crawled URL set and the URL set of having been crawled by URL manager, realize URL deduplication;Dispatcher is used for coordinating and allocating download task;Resolver is used for analyzing the page type of target website, structure, request response feature, automatically adjusting crawling parameter, optimizing page access frequency, automatic verification Captcha, analyzing page depth, compliance verification crawling content;Downloader is used for simulating user behavior downloading page;Data storage is used for storing data.The application has the advantages that: using dynamic feature identification method completes the dynamic adjustment of crawling parameter, access frequency self-adaptation, Captcha automatic processing, crawling process personification, crawling page depth controllable, crawling content compliance, realizes the adaptability, high efficiency and safety of network data acquisition process.

Embodiments of the present disclosure are directed to systems and methods for enhancing accessibility in Two-Factor Authentication (2FA). An alternative 2FA solution allows for users to choose from different methods during authentication. For example, users may opt for a voice call where they receive audio instructions that can be responded to via a device keypad. Alternatively or additionally, users may be provided with a link to a touch-based CAPTCHA. These approaches, and aspects thereof, helps ensure that all users, including those with visual impairments or other disabilities, can securely and easily complete the 2FA process, enhancing accessibility and inclusivity while maintaining robust security.

This invention relates to a method for preventing malicious CAPTCHA scraping, applied on the server side. The method includes receiving a CAPTCHA request initiated by a user, parsing and obtaining the user's IP address, device ID, and mobile phone number; generating graded IP address behavior tags, graded device ID behavior tags, and graded mobile phone number behavior tags based on the current day's request behavior and historical behavior data for the IP address, device ID, and mobile phone number; different graded behavior tags have different upper limits for daily request thresholds; comparing the current day's request threshold with a preset threshold determines whether to proceed to the next verification step or directly issue a CAPTCHA. This invention employs different verification methods for CAPTCHA requests based on tag grades, enriching verification methods, improving verification security, and effectively limiting the scraping of mobile phone CAPTCHAs.

This invention provides an image recognition method and system. The method includes: constructing a deep learning network model based on a convolutional neural network (CNN) and a long short-term memory network (LSTM); training the deep learning network model to determine a CAPTCHA recognition model; and inputting a CAPTCHA image to be recognized into the CAPTCHA recognition model to obtain a recognition result for the CAPTCHA image. The system is used to execute the above method. This invention, based on a deep learning network model, uses the entire image as input, eliminating the need for character segmentation. Problems such as high background noise, character overlap, and character distortion in CAPTCHA images can be solved through model training. Once trained, the model requires no maintenance or updates. Furthermore, the CAPTCHA recognition model, trained based on the deep learning network model constructed using CNN and LSTM, can achieve classification and extraction of the CAPTCHA image to be recognized.

An approach for improving completely automated public turing test to tell computers and humans apart (CAPTCHA) reliability for a resource. The approach receives a request for a CAPTCHA validation from a user. The approach retrieves a CAPTCHA analysis configuration associated with the user. The approach displays a CAPTCHA multi-zone display defined by the configuration. The approach receives video input containing adjunct objects, associated with objects visible on the user, from the user for the multi-zone display. The approach determines if the inputs are valid based on the CAPTCHA analysis configuration. The approach, responsive to the inputs being valid, allows access to the resource.

Methods and systems are provided for generating a fully automated common Turing Test (CAPTCHA) image. In some examples, the method includes: generating a plurality of images using a generative imaging model; providing a user with the plurality of images and a description corresponding to one of a similarity or a difference between the plurality of images; receiving a selection of an image of the plurality of images; determining whether the selection is correct based on the provided description; and outputting an indication of whether the selection is correct.

This application discloses an image reconstruction method, device, and storage medium based on a rotated CAPTCHA, comprising: acquiring a CAPTCHA image; parsing the CAPTCHA image to obtain an original rotation angle; splitting the CAPTCHA image into an inner rotated image and an outer background image, and inputting the inner rotated image and the outer background image into a visual Transformer model; using the self-attention mechanism of the visual Transformer model to capture the long-distance dependency between the inner rotated image and the outer background image, and outputting a predicted rotation angle based on the long-distance dependency; and reconstructing the CAPTCHA image using the predicted rotation angle and a preset circular weight loss function. This application effectively captures the long-distance dependency between the inner rotated image and the outer background image through the self-attention mechanism of the visual Transformer model, improving the accuracy of rotation angle prediction, thereby enhancing the reliability of CAPTCHA image reconstruction and the accuracy of security assessment.

A system and method for authenticating a user device with a CAPTCHA (completely automated public Turing test to tell computers and humans apart). A content server may receive a request from a user device to access content or a service by the content server. In response the request, the content server may require authentication of the user device through an authentication server. The user device may be granted access to the content or service upon a successfully authentication of a CAPTCHA response.

The method and system for performing a completely automated public Turing test to tell computers and humans apart (CAPTCHA). The method comprises receiving by a server a request from a service server to initiate a CAPTCHA of a user node; generating an image of a path; generating at least one target to be placed upon the path; generating an object to be placed at a start point of the path; sending the generated path, the at least one generated target, and the object as a CAPTCHA challenge to the user node for display thereon; receiving, by the server, data respective of motion of the object with respect to the path and the at least one generated target; and issuing, based on analysis of the data received data, a pass indication upon determination that the user node is operative by a human.

The system according to the embodiment aims to provide feedback based on the user's recognition rate using CAPTCHA. [Solution] A system according to an embodiment includes a selection unit, a calculation unit, a provision unit, and a presentation unit. The selection unit selects a type of CAPTCHA. The calculation unit calculates a user's recognition ratio based on the CAPTCHA selected by the selection unit. The provision unit provides feedback based on the recognition ratio calculated by the calculation unit. The presentation unit presents the feedback provided by the provision unit to the user.