45 results about "Spamming" patented technology

Disclosed are systems and methods that monitor for malicious and unauthorized behaviors, determine categories for detected malicious behaviors, determine why a domain is determined to be malicious, and provide information to users that identifies the categories and reasons as to why a domain is determined to be malicious. In some implementations, the disclosed systems and methods may be utilized to provide monitoring security to customers of a cloud service. For example, customers of a cloud service may maintain an account with the cloud service and the disclosed implementations may be utilized to protect those accounts from malicious attacks and cybercrimes such as, but not limited to, spam, phishing, malware, botnets, etc.

Embodiments of the technology described programmatically decrease the number of spam Uniform Resource locators (URLs) that are accessed from untrusted domains when the subdomain prefix is above a threshold probability of having been randomly generated. In this regard, prior to adding a discovered set of URLs to a crawl queue of a web crawler, the URLs are filtered into URLs from trusted domains and untrusted domains determined by a statistical model. The trusted domain URLs are added to the crawl queue, and the remaining URLs are sandboxed to filter out spam URLs. The subdomain prefixes of the sandboxed URLs are applied to a neural network to determine the probability that the subdomain prefixes are randomly generated. When a subdomain prefix is above a threshold probability of having been randomly generated, the subdomain is determined to be a spam subdomain and can be blocked.

Techniques herein balance the need for flexibility with the need accuracy, using a reactive approach to viral spam detection. After content (e.g., a social media platform news feed or timeline post) is created, interaction activity (e.g., content views) with the content is monitored. Based on the monitoring of the interactivity activity, it is determined whether a reactive viral spam analysis condition is satisfied for the content (e.g., because the number of content views exceeds a threshold). In response to determining that the reactive viral spam analysis condition is satisfied, a determination is made whether the content is or is not viral spam. If the content is determined to be viral spam, then it may be reported or flagged for further action (e.g., take down after manual confirmation).

The system receives a request for communication from an originator UE. The request for communication includes a unique identifier of the originator UE and a unique identifier of a receiver UE. The system obtains profile information of the originator UE including a name or a region of the originator UE. The system obtains profile information of the receiver UE including a communication history or calendar entry of the receiver UE. Based on the profile information of the originator UE and the receiver UE, the system determines whether the communication is spam. If the communication is valid, the system routes the communication to the originator UE. If the communication is spam, the system indicates to the receiver UE that there is an incoming communication that is likely spam. The system stores in a database the unique identifier of the originator UE and the determination of whether the communication is spam.

The system receives a request for communication from an originator UE. The request for communication includes a unique identifier of the originator UE and a unique identifier of a receiver UE. The system obtains profile information of the originator UE including a name or a region of the originator UE. The system obtains profile information of the receiver UE including a communication history or calendar entry of the receiver UE. Based on the profile information of the originator UE and the receiver UE, the system determines whether the communication is spam. If the communication is valid, the system routes the communication to the originator UE. If the communication is spam, the system indicates to the receiver UE that there is an incoming communication that is likely spam. The system stores in a database the unique identifier of the originator UE and the determination of whether the communication is spam.

To provide a training mail system capable of performing actually experienced junk mail training and junk mail education for acquiring knowledge by viewing contents in cooperation with each other.SOLUTION: A training mail system 100 includes user terminals 110, manager terminals 120, and a server 130, and browsers 121 of the manager terminals 120 display a training execution setting screen 124 on which training name information TG1 and content information ED2 for training can be freely designated. When the educational name information ED1, the trainee name information TG1, and the educational content information ED2 are inputted and designated on the educational implementation setting screen 124, the server 130 registers the educational name information ED1, the trainee name information TG1, and the educational content information ED2, and the server 130 transmits the educational guidance e-mail EDM related to the educational content information TG1 to the user terminals 110 based on the trainee information associated with the registered trainee name information ED2.SELECTED DRAWING: Figure 1

The invention provides a document classification method and device based on a large model, an intelligent agent and electronic equipment, and relates to the technical field of artificial intelligence, in particular to the technical fields of natural language processing, large models and the like. The method can be applied to scenes of enterprise internal document management based on artificial intelligence, patient record management of medical institutions, news classification, social media topic classification, spam filtering, medical literature classification, legal document classification and the like. According to the specific implementation scheme, an input document is obtained; determining the document type of the input document, wherein the document type is divided into a streaming document and a format document; generating corresponding target prompt word information according to the document type; document classification is conducted on the input document based on the target prompt word information through the multi-modal large model, the category of the input document is obtained, and the category of the input document refers to the semantic category of the input document. The prediction performance of the document classification system can be improved, and the prediction time can be shortened.

In some embodiments, the present disclosure provides an exemplary method that may include steps of receiving a notification to engage a transmission guard bot in a communication session; generating a trained transmission guard bot configured with communication capabilities to engage the communication session; engaging the trained transmission guard bot into the communication session between the plurality of computing devices associated with the plurality of users; utilizing the trained transmission guard bot to continually monitor a plurality of content data associated with the communication session for a predetermined period of time; detecting a suspicious content data point within the plurality of content data associated with the communication session based on the continual monitoring of the at least one transmission guard bot; determining a risk assessment metric associated with the communication session; and invoking an action related to spam prevention via the at least one trained transmission guard bot.

The embodiment of the invention provides a junk mail filtering method and device, equipment, a storage medium and a program product. The method comprises the following steps: preprocessing mail contents of mails to obtain mail text information related to mail classification; text feature extraction is conducted on the mail text information, a text feature vector corresponding to the mail text information is generated, the text feature vector comprises weight values corresponding to a plurality of segmented words in the mail text information, and the weight values are used for indicating the probability that the segmented words belong to spam content; calling a trained mail classification model according to the text feature vector, and determining mail classification information corresponding to the mail; the mail classification model is obtained by training based on text feature vectors of a plurality of historical mails; and if the mail classification information is a normal mail type, receiving the mail, and if the mail classification information is a junk mail type, rejecting the mail. According to the method, the spam filtering accuracy is improved.

A spammy app detection system may search a database for any new social media application discovered during a recent time period. A spammy app detection algorithm can be executed on the spammy app detection system on an hourly basis to determine whether any of such applications is spammy (i.e., posting to a social media page anomalously). The spammy app detection algorithm has a plurality of stages. When a new social media application fails any of the stages, it is identified as a spammy app. The spammy app detection system can update the database accordingly, ban the spammy application from further posting to a social media page monitored by the spammy app detection system, notify an entity associated with the social media page, further process the spammy application, and so on. In this way, the spammy app detection system can reduce digital risk and spam attacks.

Aspects of the disclosure relate to detecting and protecting against cybersecurity attacks using unprintable tracking characters. A computing platform may receive a character-limited message sent to a user device. Subsequently, the computing platform may detect that the character-limited message sent to the user device includes suspicious content. Then, the computing platform may generate a modified character-limited message by inserting one or more special characters into the character-limited message and cause transmission of the modified character-limited message to the user device. Next, the computing platform may receive, from the user device, a spam report that includes the modified character-limited message. Then, the computing platform may identify a presence of the one or more special characters included in the modified character-limited message and adjust one or more filters based on the identification.

Described herein are techniques, devices, and systems for utilizing subscriber and user equipment (UE) related content to generate limitations of rich communications service (RCS) capabilities as antispam security measures. The RCS capabilities limitations can be utilized to strip RCS capabilities from possible malicious UEs. The UEs can be identified as the possible malicious UEs by scanning telecommunications networks for behavior of the UEs that is identified as being possible malicious behavior. Stripping the RCS capabilities can include downgrading capabilities of the possible malicious UEs from RCS capabilities to short messaging service (SMS) / multimedia messaging service (MMS) capabilities. Communications associated with the possible malicious UEs being identified as malicious UEs can be monitored and analyzed to restrict communication of communications identified as malicious messages.

The invention discloses an improved GADT model auxiliary junk mail detection method based on a genetic algorithm, and relates to the technical field of junk mail detection and classification, and the method comprises the following steps: S10, carrying out structured preprocessing on an input text, including text standardization, stop word deletion and stem extraction; according to the method, feature space redundancy and noise are effectively reduced, key semantic information is reserved, and the data scale is compressed by performing structured preprocessing on the mail text and combining TF-IDF feature coding and PCA dimension reduction; a decision tree pruning parameter confidence factor is adaptively optimized by using a genetic algorithm, the complexity and generalization ability of the decision tree are dynamically balanced, and the classification accuracy and the model robustness are remarkably improved; the feature dimension reduction and model optimization cooperate to reduce the training reasoning complexity and improve the detection real-time performance, and the method is significantly superior to the prior art in accuracy, robustness and calculation efficiency, and has good expansibility and application and popularization value.

The application provides an email threat perception system, belonging to the field of network security and email protection, and researches and practices email security threat perception technology, utilizes an email behavior detection model and a machine learning model to perform multi-dimensional and multi-level deep analysis on emails, so as to identify abnormal email behaviors, discover phishing links and sensitive contents, etc. On this basis, an active and low false alarm rate email security threat perception system is realized, which detects and filters spam emails, phishing emails and emails containing sensitive contents, and improves the security of email applications.

In some embodiments, the present disclosure provides an exemplary method that may include steps of receiving a request for a plurality of data items from a computing device; determining at least one pattern for at least one metric associated with the computing device; generating at least one digital code based on the at least one pattern meeting a predetermined metric threshold, the at least one digital code comprising access to a plurality of resources; assigning the at least one digital code to the computing device to form at least one assigned digital code; and allowing access to the plurality of resources to facilitate performing a domain name availability determination for the plurality of data items.

Systems and methods for determining whether a linked content page may include spamming, malicious, and / or otherwise undesirable content. The linked content page may be crawled, scraped, and / or parsed to extract various information associated with the text, media items, and / or structure of the linked content page. The text, media, and / or structure information may be analyzed and processed to generate one or more textual features, media features, and / or structural features, which may then be processed by a trained machine learning model to determine whether the content page includes spamming, malicious, and / or otherwise undesirable content.

The disclosed invention pertains to a software system for secure digital communication. It involves generating and assigning a unique email address, structured with a prefix, domain and / or subdomain, to an external user for communication with an internal user. The system monitors subsequent communication, comparing it with the assigned email address to detect any compromise. In case of detected malicious intent, the system initiates appropriate countermeasures, enhancing the overall security of digital communication.

The embodiment of the invention provides an E-mail secure delivery method and related equipment, and belongs to the technical field of information security. The method comprises the following steps: carrying out explicit content extraction on a received email to obtain email explicit information; performing first classification processing on the emails according to the email explicit information to obtain a first classification result; when the first classification result represents the junk mail, intercepting the E-mail; under the condition that the first classification result shows the credible email, delivering the email to a recipient mailbox; and under the condition that the first classification result shows the suspicious mail, delivering the e-mail to a recipient mailbox, and carrying out second classification processing on the link pointing content of the link domain name in the e-mail to obtain a second classification result. According to the invention, the E-mail delivery security and timeliness can be improved.

Embodiments of a method for facilitating spam blocking in a tiered software framework include: determining that a message template is generated in the tiered software framework, parsing the message template, automatically performing a semantic search for regulated content in the parsed message template, assigning a score to the message template based on the semantic search, and responsive to the score being higher than a predetermined threshold, blocking generating of any message from the message template. The tiered software framework comprises a first tier, a second tier, and a third tier, the second tier comprises accounts of a first plurality of subscribers, the third tier comprises subaccounts of the accounts, the subaccounts associated with a second plurality of subscribers, and the message template is associated with one of the subaccounts in the third tier.

The present invention discloses a spam detection method based on an email service asset co-occurrence graph. The method includes: an offline training phase for a machine learning model: obtaining header information for each sample email in a sample set; the sample set includes several legitimate emails and several spam emails; extracting preset fields from the header information of each sample email, constructing a co-occurrence subgraph corresponding to each sample email, and then merging the obtained co-occurrence subgraphs to obtain an email service asset co-occurrence graph; based on the co-occurrence subgraphs of the sample emails and the email service asset co-occurrence graph, using subgraph representation learning technology to learn the subgraph representation of the corresponding sample email and label it; using the labeled subgraph representation to train the machine learning model; an online detection phase: inputting the subgraph representation of the email to be detected into the trained machine learning model, and outputting the probability that the email to be detected is spam. The present invention makes full use of email asset information for spam detection.

Via a DNS record, an Internet domain designates a website as a Domain Email Authority (DEA): a consolidated entity that collects, validates, and stores all email-related policies of the domain to distribute them to the DNS, email servers, email clients, and end-users. Simple embodiments of this invention can be implemented without changes to existing email standards, servers, or clients, and can provide considerable benefits such as enhanced security and reduced spam. Also described are more advanced embodiments that can be introduced gradually through small modifications to specific standards, protocols, and specific components of email servers and clients. Given that the email standard is mature and highly resistant to change, the DEA is designed to be an inexpensive means for experimenting with new email features such that new features do not require significant changes or end-to-end adoption by the entire email ecology.

A system is configured to analyze large volumes of sample emails from past spam campaigns to identify homogeneous features, as well as systematically heterogeneous features, which spam originators fail to obfuscate. By extracting origin-referencing features therefrom, the system predicts that spam originators will mass-acquire domain names at certain registrars for the purpose of future spam floods, and repeatedly and periodically analyzes domain name records on an automated basis to identify domain names which will imminently be utilized as spam origins. Since it may be necessary to block tens of thousands of domains preemptively to avert spam floods, performance of such large-scale analysis by a computing system allows spam origins to be predicted on a timely basis within a day of spam floods being deployed, and domain lists to be generated and configured responsively in time to prevent the spam floods.

The invention relates to a phishing mail interception system and method, and belongs to the technical field of information security, and the system comprises a mail preprocessing module which is used for receiving a mail in an HTML format, carrying out the structural analysis of the mail, and carrying out the preprocessing of the analyzed mail, and obtaining a target mail; the feature extraction and recognition module is used for extracting CSS attributes related to text hiding in a target mail, performing feature vector fusion and standardization on the extracted features to obtain a target feature vector, predicting the target feature vector based on a hybrid model of SVM and LSTM to obtain a prediction result of the mail, and outputting the prediction result of the mail. The prediction result comprises a judgment result and confidence of a normal mail or a suspicious CSS hidden mail; and the multi-dimensional decision-making module is used for acquiring the attribute information of the sender of the mail, and comprehensively evaluating the prediction result based on the attribute information to obtain the decision-making result of the mail. According to the system, the junk mail recognition rate is improved, and information leakage is reduced.

This invention discloses a spam classification method, apparatus, device, and storage medium, implemented through an extraction module, a detection module, a classification module, and a disposal module. The extraction module can be customized according to the specific needs of spam classification. The detection module employs multiple fusion feature vector techniques based on an LLM pre-trained model and feature engineering to achieve multimodal detection of spam metadata, text, images, hyperlinks, and visual data. The classification module, based on the fusion feature vectors, uses TabNet to enhance the ability to learn features and further subdivide spam / emails. Simultaneously, the disposal module provides user-customizable configurations to meet users' needs for customized and automated spam / email disposal. This solution not only improves the accuracy of spam detection but also provides more personalized settings, enabling users to better manage email classification rules, reduce false positives, and ensure that valuable emails are not misclassified.

The invention provides a junk mail identification method and device, electronic equipment and a storage medium. The junk mail identification method comprises the following steps: in response to a detected first mail sent to a first receiving end, detecting the first mail according to a detection rule; sending the first mail to the first receiving end according to a normal mail mode in response to the condition that the time consumed for detecting the first mail reaches a preset duration or the detection of the first mail fails, and continuing to asynchronously detect the first mail according to the detection rule to determine whether the first mail is abnormal; processing the first mail in the first receiving end in response to the fact that the result of asynchronously detecting the first mail shows that the first mail is abnormal; and in response to the received related information of the abnormal mail, determining historical mails which conform to the related information and are not determined to be abnormal from the historical mails of the first receiving end according to the related information, and processing the historical mails. According to the method disclosed by the invention, the delay of receiving the first mail by the user can be avoided, and historical mails can be traced.

A method for detecting Arabic phishing emails includes connecting a log management solution to an email management solution that includes a spam repository and one or more emails. The spam repository includes one or more Indicators of Compromise (IoCs) that is digital information associated with a cyberattack. An IoC index of the log management solution is populated with the IoCs. The log management solution searches the emails using the IoC index and flags one or more potential phishing emails when an email matches an IoC in the IoC index. The log management solution assigns an authenticity score to each of the potential phishing emails and generates a potential phishing email report containing the potential phishing emails and the authenticity score assigned to each of the potential phishing emails. Based on the potential phishing email report, an assigned user performs one or more remediation actions.

According to one embodiment, the electronic device may include a communication circuit, a memory that stores instructions and includes one or more storage media, and at least one processor that includes a processing circuit. When the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to receive a message from an external electronic device using the communication circuit, identify the message as an allowed message using the content of the message and the sender number of the message, identify a category of the message and a filtering level set according to the category based on the content of the message, obtain information regarding the probability that the message is a spam message that is distinguished from the allowed message, identify the message as the spam message based on identifying that the probability is within the probability range according to the filtering level, and maintain the message as the allowed message based on identifying that the probability is outside the probability range according to the filtering level.

Embodiments of a method for facilitating spam blocking in a tiered software framework include: providing instructions to a machine learning module (MLM) to generate a threshold for classifying spam in messages generated in a tiered software framework. The instructions include inputs comprising government regulations; carrier guidelines; feedback on previously sent messages; and previously flagged messages. The instructions specify that the threshold is to prevent false positives while allowing false negatives. The method further includes, receiving the threshold according to the instructions from the MLM; parsing a message; automatically performing a semantic search using natural language processing for regulated content in the parsed message by comparing semantics of text of the parsed message to the inputs to find matches; assigning a score to the message based on matches found; and responsive to the score being higher than the threshold, blocking sending the message from the tiered software framework.

The system receives a request for communication from an originator UE. The request for communication includes a unique identifier of the originator UE and a unique identifier of a receiver UE. The system obtains profile information of the originator UE including a name or a region of the originator UE. The system obtains profile information of the receiver UE including a communication history or calendar entry of the receiver UE. Based on the profile information of the originator UE and the receiver UE, the system determines whether the communication is spam. If the communication is valid, the system routes the communication to the originator UE. If the communication is spam, the system indicates to the receiver UE that there is an incoming communication that is likely spam. The system stores in a database the unique identifier of the originator UE and the determination of whether the communication is spam.

The invention relates to the field of mail recognition, and particularly provides a junk mail recognition method based on multi-modal features and adaptive learning, which comprises the following steps: S1, analyzing an input mail, extracting multi-modal feature vectors in parallel, and constructing a comprehensive feature vector; s2, inputting the extracted multi-modal feature vector into a feature fusion network based on attention to generate a unified mail comprehensive feature representation; s3, inputting the comprehensive feature representation into a classifier to obtain a prediction result and confidence of whether the mail is a junk mail; and S4, continuously operating the system, and driving online optimization of the model by utilizing feedback data. According to the scheme, high-performance and self-evolution intelligent spam filtering is realized.