26 results about "Internet fraud" patented technology

The invention provides a counterfeit website detection method and device based on a large language model, and the method comprises the steps: inputting website information into a detection model, obtaining a discrimination result outputted by the detection model, and determining whether a to-be-detected website is a counterfeit website or not; wherein the detection model is obtained by constructing a reward function through a group mutual anti-rank index, constructing unsupervised contrast feedback based on a set of similar websites and training a large language model. According to the method, the strong semantic comprehension and generation capability of the large language model is utilized, and the group comparison feedback reinforcement learning mechanism and the fine-grained analysis of implicit semantic enhancement are combined, so that counterfeit network fraud activities are efficiently and accurately identified and prevented.

A system and method for detecting fraud may scan (e.g. by computer server) a target website provided by another server to identify products provided by the website. Based on the scanning, a process may calculate probabilities for combinations of the identified products, where a cost for each combination equals a cost of a new transaction to take place at the target website, and generate an authentication score for the transaction based on the calculated probabilities.

The invention provides a fraud website detection method and device based on a multi-mode large language model, and relates to the technical field of network fraud detection. The method comprises the following steps: performing image processing on a webpage screenshot to obtain an enhanced screenshot and a first judgment basis; performing graph model construction according to the html source code to obtain an html graph model; based on a GPT-4o model, generating a second judgment basis according to the enhanced screenshot, a preset real label and the first judgment basis; on the basis of the adjustable temperature coefficient, the multi-modal large model is used for fraud website detection reasoning, and the multi-modal large model after fine adjustment and a fifth judgment basis are obtained; performing sample construction through the scoring model to obtain a selected sample and a rejected sample; and performing reinforcement learning training on the fine-tuned multi-modal large model by using the selected sample and the rejected sample, and performing fraud website detection by using the optimized multi-modal large model. The method is an efficient and accurate fraud website detection method based on the multi-modal large language model.

The embodiment of the invention provides a model training method and a telecommunication network fraud behavior recognition method and device, and relates to the technical field of financial science and technology, the technical field of machine learning and the technical field of information security. The model training method comprises the steps of performing feature mining on historical transaction behavior data to obtain a plurality of features; according to each piece of historical transaction behavior data, extracting data corresponding to a plurality of features to obtain an original data set; dividing the original data set into N-fold data, and for the N-fold data, determining a replacement importance score mean value of each feature in the plurality of features by adopting a multi-fold cross calculation mode; selecting important features from the plurality of features based on the replacement importance score mean value of the features, and extracting a target data set corresponding to the important features based on the original data set; and training based on the target data set to obtain a telecommunication network fraud behavior recognition model. The telecommunication network fraud behavior recognition model provided by the invention has relatively high accuracy and relatively strong generalization ability.

The invention discloses a multi-dimensional graph series-parallel and visualization method for telecommunication network fraud cases based on a graph database. According to the method, intelligent series-parallel analysis across time-space cases is realized by constructing a knowledge graph containing various entities such as cases, personnel, accounts and equipment and deeply fusing a hard association matching algorithm and a soft similarity graph algorithm. The system has the functions of white list filtering, time sequence behavior analysis, NLP information extraction and the like, and can effectively identify criminal gangs, track fund flow directions and mine crime modes. And finally, dynamic visual display is carried out through a plurality of interactive views such as a force-oriented graph, a time axis and a mulberry-based graph, and clue intelligent pushing and report automatic generation are supported. According to the method, the case association mining depth, the serial-parallel analysis efficiency and the interpretability of a complex network are remarkably improved, and an efficient technical support is provided for the public security organization to fight against telecommunication network fraud.

The invention discloses an anti-telecommunication network fraud system based on big data analysis, and belongs to the technical field of network security supervision, the system comprises an IDC server module, an information tracking module, a network transmission module and a central processing module, the information tracking module comprises an information acquisition unit, a modeling analysis unit and an effect verification unit, a firewall module, a safety management module and a safety operation and maintenance module are arranged between the network transmission module and the central processing module. According to the anti-telecommunication network fraud system based on big data analysis, through deep analysis of big data and real-time supervision and regular patrol of the big data, comprehensive evaluation analysis of network security is carried out, the overall security condition of the network is judged, then the network is managed reasonably, the occurrence of network fraud is reduced, and the security of the network is improved. And meanwhile, an emergency processing scheme is established, so that when network security vulnerabilities occur, security transfer of the data can be quickly completed, and the security of the data is ensured.

This application discloses a method and system for consolidating evidence of network fraud through multimodal semantic consistency verification, comprising: collecting and modally identifying multimodal electronic evidence and generating original data fingerprints; extracting semantic information from each modal of evidence across five dimensions: time, amount, identity, behavior description, and geographical location; constructing a cross-modal evidence semantic association graph with a heterogeneous graph structure including evidence nodes, element nodes, and relational edges, and establishing attribution edges and cross-modal association edges based on element categories using differentiated semantic similarity calculation methods; generating initial feature vectors for each node, inputting the semantic association graph into a graph attention network model for consistency inference, performing consistency, contradiction, and uncertainty classification on cross-modal association edges, and obtaining a global consistency score; and performing differentiated on-chain consolidation operations based on the score to generate consolidation certificates. This invention can automatically discover semantic contradictions between different modalities of evidence, improving the quality of electronic evidence consolidation.

The present invention provides a fraudulent website detection method and device based on a large multimodal language model, relating to the technical field of network fraud detection. The method comprises: performing image processing on a webpage screenshot to obtain an enhanced screenshot and a first judgment basis; constructing a graph model based on HTML source code to obtain an HTML graph model; generating a second judgment basis based on the enhanced screenshot, a preset true label, and the first judgment basis based on a GPT-4o model; performing fraudulent website detection inference using the large multimodal model based on an adjustable temperature coefficient to obtain a fine-tuned multimodal model and a fifth judgment basis; constructing samples using a scoring model to obtain selected samples and rejected samples; using the selected samples and rejected samples to perform reinforcement learning training on the fine-tuned multimodal model, and using the optimized multimodal model to detect fraudulent websites. The present invention provides an efficient and accurate fraudulent website detection method based on a large multimodal language model.

This invention proposes a chat topic recognition method and system based on text tag prediction. The method includes the following steps: acquiring and preprocessing the chat data information to be processed; processing the preprocessed chat data information using a trained deep learning model, including sentence encoding and sequence labeling; and identifying specific content from the chat data information using the deep learning model and further processing it. By introducing Sentence Bert to extract semantic features from chat statements, and using sentences as semantic units input into the model, the length limit of the feature labeling network is greatly expanded. The feature labeling method is used to label behaviors commonly seen in online fraud, ensuring that even if the wording is updated, the truly crucial inducement behaviors remain largely unchanged. By modifying the convolutional neural network model, the model can perform sequence labeling tasks while retaining the high inference performance of the convolutional neural network.

The invention relates to an information acquisition analysis and intelligent detection closed-loop linkage system and method for an internet fraud-related carrier, and belongs to the technical field of network security and fraud-related risk disposal. Aiming at the problems of disjunction of acquisition and detection, leak detection of homologous carriers, low response efficiency, no closed loop of results and the like in the prior art, a collaborative linkage architecture of an acquisition system, a detection system and a management and control platform is constructed; through black and white list query, standardized feature extraction, multi-model fraud-related detection, homologous clue supplementary collection, task priority management and result double-path closed-loop feedback, full-process closed-loop management and control of collection-detection-feedback-disposal is realized. According to the method, the accuracy, the coverage rate, the response efficiency and the overall prevention and control capability of fraud-related risk disposal are effectively improved.

The invention discloses an anti-fraud method applied to a remote control scene. The remote control platform plays a role in equipment hardware information management, equipment network information management, user information management, user behavior information collection and management and the like. In order to cope with the occurrence of a network fraud case in a remote control scene, an anti-fraud coping strategy is provided in three stages of risk prediction and avoidance in advance, in-event risk detection and post-event risk feedback, and fraud in remote control is fully avoided.

Mobile phone software is used for network social contact, has various methods for preventing network fraud, and helps a user to judge network fraud through measures of logging in a historical list by the user, verifying a video through an address, forcing the video, evaluating various authenticity basis and the like. By adopting the methods, the network fraud can be effectively, conveniently and quickly prevented, and the labor cost of a software operator is saved.

Some embodiments implement a targeted notification of potential victims of online fraud, such as fishing, among others. A security server protects a plurality of client devices by using telemetry data harvested from each device to construct a device-specific client profile. The client profile indicates a typical manner in which the respective device is used (e.g., which applications are installed and how much each installed application is being used). Features extracted from incoming messages are used to identify fraudulent messages and divide an incoming message stream into clusters. In response to identifying a cluster including fraudulent messages, some embodiments identify the recipients of cluster messages, and select a notification target from among the protected client devices according to a similarity between a client profile of the notification target and client profiles of the message recipients. A security notification is sent to the notification target.

Provided are a risky website detection method and apparatus based on a large language model, the method comprising: inputting website information into a detection model to obtain a discrimination result, which is output by the detection model, so as to determine whether a website to be subjected to detection is an impersonation website, wherein the detection model is obtained by constructing a reward function by means of a group-wise reciprocal rank index, constructing unsupervised contrastive feedback on the basis of a set of similar websites, and training a large language model. The present application efficiently and accurately identifies and prevents impersonation cyber fraud activities by using strong semantic understanding and generation capabilities of the large language model and in view of a group-wise contrastive feedback reinforcement learning mechanism and fine-grained analysis of latent semantic enhancement.

The embodiment of the present application discloses a network fraud threat identification method and device based on big data analysis, which relates to the field of network security technology and is invented to reduce the losses suffered by users from network fraud. The method includes: generating detection assets according to network fraud assets in a preset fraud threat asset database; sending the detection assets to multiple detection probes so that each detection probe determines whether the network asset on the host corresponding to the detection probe is a suspicious asset based on the detection asset; if the network asset is a suspicious asset, the network asset is determined as an asset to be identified; the asset to be identified is matched with the network fraud asset in the preset fraud threat asset database; if the match is unsuccessful, the interface of the big data platform is called to obtain the network data corresponding to the asset to be identified from the big data platform; based on the network data, determine whether the asset to be identified is a network fraud asset. The present application is applicable to identifying suspicious network assets.

The application relates to the technical field of network security, and discloses a network fraud explainable detection and digital evidence diversion method based on community-speech-platform feature fusion. The application obtains a network interaction observation object to be detected and performs de-identification processing; generates community relationship evidence data, speech promotion evidence data and platform behavior evidence data from the observation object; encodes and maps the three types of evidence data to a shared representation space respectively, generates fusion weights corresponding to the observation object, and fuses the fusion weights to obtain evidence chain fusion representation; generates a risk identification result containing a risk category and a risk value according to the evidence chain fusion representation; generates an evidence object index according to the risk identification result and a contribution parameter; and stores the risk identification result and the evidence object index in association to generate digital evidence diversion data. The application can protect user privacy and data security while providing traceable data organization support for subsequent review, audit and source hierarchical evaluation.

The application discloses a fraud-preventing method applied to a remote control scene. The application takes a remote control platform as a role of device hardware information management, device network information management, user information management and user behavior information collection and management. In order to cope with the occurrence of network fraud cases in the remote control scene, the application provides fraud-preventing coping strategies in three stages of "prior risk prediction and avoidance", "in-process risk detection" and "post-process risk feedback", so that the remote control is fully prevented from being frauded.

A publicity method, system, storage medium and electronic device for countering online fraud, which relates to the field of information technology. The method includes: obtaining a list of users to be called; determining the current called user in the list of users to be called, and determining a first fraud strategy based on the basic user information of the current called user, where the first fraud strategy includes a fraud type, a first fraud level, a first fraud script, and a first fraud tone; obtaining a first feedback result of the current called user on the first fraud plan, and calculating an anti-fraud score value of the current called user based on the first feedback result; when the anti-fraud score value is greater than a score threshold, adjusting the first fraud strategy to obtain a second fraud strategy; obtaining a second feedback result of the current called user on the second fraud plan, generating an anti-fraud publicity report based on the first feedback result and the second feedback result, and sending the anti-fraud publicity report to the current called user. Implementing the technical solution provided by this application can improve the effectiveness of anti-fraud publicity.

The invention discloses an Internet fraud identification method and system based on graph path information interaction. The method comprises the following steps: 1) constructing an Internet scene relation network graph; 2) sampling a variable-length path; 3) embedding a path taking an event as a unit; 4) performing path embedding enhancement on the associated behavior; 5) interacting and fusing path information; and 6) detecting the associated and fused internet fraud. According to the method, variable path sampling, a path embedding technology taking an event as a unit, a path embedding enhancement technology of associated behaviors and a path information interaction fusion strategy are adopted, so that the capability of a GNN algorithm in the aspect of coping with a long-range association graph structure is remarkably improved, and the limitation of the GNN algorithm in the task is effectively made up.

The invention relates to the field of telecommunication network fraud prevention, in particular to a telecommunication network fraud scene analysis engine design method, system and device and a medium. The method comprises the steps that an original data set is acquired and screened; extracting original features corresponding to the screened original data set through a preset fraud scene model, and performing weighted scoring on the original features to obtain weighted features; converting the weighted features into a data set of an associated scene; and performing fraud scene analysis on the data set of the associated scene through a preset fraud scene model to obtain a scene analysis result, and safely outputting the scene analysis result through an open interface. According to the method, an original data set is processed by utilizing scene model instantiation configuration, an open associated scene data set is generated by utilizing different application scenes, and model arrangement and task scheduling are carried out by multiple model parties.

The invention discloses an anti-fraud practical training method and device in the telecommunication network fraud field and a medium, and the method comprises the steps: carrying out the modeling based on network communication data, and obtaining a plurality of anti-fraud models; evaluating the plurality of anti-fraud models by taking the identification range and the identification precision as standards to obtain a plurality of evaluation scores; and according to the performance index of the network communication data, optimizing the anti-fraud models which do not reach a preset standard in the plurality of evaluation scores to obtain an anti-fraud model set, and carrying out anti-fraud practical training on the user through the anti-fraud model set. According to the anti-fraud practical training method and device in the telecommunication network fraud field and the medium provided by the invention, a plurality of established anti-fraud models are evaluated and optimized by taking the recognition range and the recognition precision as standards, so that the finally obtained model can cover and recognize more fraud types and scenes, the recognition accuracy is ensured, and the fraud training efficiency is improved. The problem that it is difficult to simulate the fraud form according to the actual characteristics of the network fraud and carry out anti-fraud practical training on the user can be solved.

The invention discloses a telecommunication network fraud damage mode analysis method, which belongs to the technical field of mode analysis, and comprises the following steps of: through an LERT model, carrying out part-of-speech tagging, named entity recognition and dependency syntax analysis on sentences in a desensitization alarm text to obtain trigger words so as to form embedded vectors; through a MoE model, according to the embedded vector, obtaining weight coefficients corresponding to a plurality of experts, so as to screen the previous expert to execute processing, and combining to obtain a processing result, so as to obtain a candidate argument tag corresponding to each trigger word, and form an output tag sequence corresponding to the sentence; and according to the tag sequence, in combination with the embedded vector, obtaining a classification role tag through a softmax classification layer of the MoE model. Through the design of the multi-task collaborative architecture and the MoE model, the problems of feature expression singleness, behavior association fragmentation, event extraction and mode mining disjunction, insufficient dynamic adaptability and the like are effectively solved.

The application discloses an old-age anti-fraud prevention and control intelligent assistant platform based on artificial intelligence and belongs to the technical field of network security.The platform comprises a website security evaluation module, a user behavior analysis module, a matching judgment module and a behavior risk protection module; the website security evaluation module collects website text data, determines whether a website is related to fraud after extracting fraud risk features by means of a fraud risk category model; the user behavior analysis module obtains user mobile phone daily behavior data, divides group categories and establishes individual behavior baselines; the matching judgment module performs matching analysis on the operation behavior data of the old-age group on the related fraud websites and the individual behavior baselines, generates a behavior risk score, and triggers the behavior risk protection module when the behavior risk score exceeds 30 points; and the behavior risk protection module immediately forcibly terminates the related operation and sends an alarm.The application can effectively prevent and control network frauds suffered by the old-age people and improve the anti-fraud protection capability through the collaborative work of the multiple modules.

The present disclosure provides a method for detecting scam website middle pages and an electronic device, the method comprising: obtaining a webpage address and constructing a sample library based on the webpage address; extracting features of samples in the sample library to obtain target features; using the target features as training samples to iteratively train a convolutional neural network and obtain performance information of the neural network after each iteration; performing back propagation on the performance information of the neural network to update parameters of the convolutional neural network and save gradient values of the back propagation; wherein the performance information of the neural network is the accuracy of detecting scam website middle pages; in response to determining that the trained convolutional neural network meets a preset convergence condition, stopping updating the parameters of the convolutional neural network and outputting a model for detecting scam website middle pages. The present application can mark and detect that a user is diverted or jumped to a middle page of a scam website, thereby addressing the problem of network fraud under a complex network.

The invention discloses a network fraud early warning method on a mobile terminal, and belongs to the technical field of fraud early warning. The system mainly comprises a monitoring analysis layer, a multi-mode output engine and an early warning management module. The monitoring analysis layer comprises a monitoring module and an analysis module, the monitoring module is used for monitoring whether the behavior of the subject is triggered or not, and the analysis module is used for uploading subject information to a server to analyze whether the subject is involved in fraud or not; the multi-modal output engine comprises a visual early warning unit, a physical feedback unit and an authority management module; the visual early warning unit comprises a banner notification reminding module and a Toast reminding module, the physical feedback unit comprises a vibration reminding module and a voice broadcast reminding module, and the authority management module is used for enabling a user to customize and select switch banner notification reminding and voice vibration reminding. According to the network fraud early warning method on the mobile terminal, the effect of combining multiple early warning modes is achieved.

The present invention proposes a social worker robot simulation method for loan investment network fraud, which belongs to the field of artificial intelligence / social engineering. Specifically: first, set up a number of social worker robots with different attributes according to actual needs, and configure user attributes for each social worker robot; fill in the micro-loan application form on each loan platform according to the attribute value, and leave the personal information of the social worker robot to the fraudster; then, build a behavior, language and voice database that conforms to the basic personality of the social worker robot, as well as a fraud process archive; then, the social worker robot interacts with the fraudster, and retains all information in the database; when the fraudster induces the social worker robot to transfer money, the social worker robot sends a transfer failure picture with a Trojan program implanted, tracks the fraudster and traces the source and feeds back to the public security department. The present invention is simple to operate and has strong practicality, which greatly improves the implementation efficiency.