Spam detection and message tagging in telecommunications networks
The invention relates to tagging messages on a telecommunications network to convey, to the receiving device, information regarding the message, such as potential malicious nature and intent. In an example, a telecommunications network node receives a request to transmit an SMS message from a first mobile device to a second mobile device. The telecommunications network node uses a fraud detection module to determine a likelihood of harm, an extent of possible damage and a category of the SMS message. Using the output of the fraud detection module, the telecommunications network node ascribes to the SMS message a message modification attribute value, for example a TP-PID value. The modified message is transmitted to the second mobile device, where it is displayed with a warning.
1 . A network node in a telecommunications network for tagging messages, the network node comprising a non-transitory computer-readable medium having instructions stored thereon, where the instructions when executed by one or more processors of the network node cause the network node to:
receive, at the network node of the telecommunications network, a request to deliver a Short Message Service (SMS) message from a first mobile device to a second mobile device;
processing first metadata associated with the SMS message to determine a spam likelihood indicator value for the SMS message,
wherein the spam likelihood indicator value is indicative of whether the SMS message is a spam message;
generate, by the network node, a message modification attribute value using the spam likelihood indicator value;
modify the SMS message using the message modification attribute value to obtain a modified SMS message, wherein modifying the SMS message comprises updating a Transfer Protocol-Protocol Identifier (TP-PID) value of the SMS message to obtain an updated TP-PID value; and
transmit, by the network node, the modified SMS message to the second mobile device.
2 . The network node of claim 1 , wherein the instructions further cause the one or more processors of the network node to:
receive, at the network node of the telecommunications network, a second request to deliver a Multimedia Messaging Service (MMS) message; and
modify the MMS message by updating a header of the MMS message.
3 . The network node of claim 1 , wherein the first metadata comprises at least one of:
a record of recent messages sent from the first mobile device,
a location of the first mobile device when requesting to deliver the SMS message,
a local time of the second mobile device, or
a messaging history between the first mobile device and the second mobile device.
4 . The network node of claim 1 , wherein processing the first metadata comprises generating a first output indicating a classification of the SMS message into one of a spam message, phishing message, or benign message.
5 . The network node of claim 1 , wherein the TP-PID value comprises:
a first value segment indicating whether the SMS message is malicious;
a second value segment indicating a category of harm associated with the SMS message, if any; and
a third value segment indicating a severity of harm associated with the SMS message, if any.
6 . The network node of claim 1 , wherein the instructions further cause the one or more processors of the network node to:
using a user profile associated with the second mobile device, determine to send the modified SMS message to a spam folder associated with account of the second mobile device.
7 . The network node of claim 1 , wherein the instructions further cause the one or more processors of the network node to:
receive user input from the second mobile device comprising the SMS message being blocked and reported; and
using the user input, create a user profile associated with the second mobile device.
8 . The network node of claim 1 , wherein the instructions further cause the one or more processors of the network node to:
receive user input from the second mobile device comprising the SMS message being blocked and reported;
using the user input, create a sender profile associated with the first mobile device; and
transmit the sender profile.
9 . The network node of claim 1 , wherein the instructions further cause the one or more processors of the network node to:
using a mobile application on the second mobile device, display the SMS message with a warning notification,
wherein the warning notification is based on the updated TP-PID value.
10 . The network node of claim 1 , wherein the instructions further cause the one or more processors of the network node to use the spam likelihood indicator value to determine the TP-PID value by:
comparing the spam likelihood indicator value against a threshold probability to determine a severity of the SMS message; and
based on the comparing, assigning the SMS message to a predefined TP-PID value symbolizing the severity of the SMS message.
11 . A method for tagging messages being communicated via a telecommunications network, the method comprising:
receiving, at a network node of the telecommunications network, a request to deliver a Short Message Service (SMS) message from a first mobile device to a second mobile device;
processing first metadata associated with the SMS message to determine a spam likelihood indicator value for the SMS message,
wherein the spam likelihood indicator value is indicative of whether the SMS message is a spam message;
generating, by the network node, a message modification attribute value using the spam likelihood indicator value;
modifying the SMS message using the message modification attribute value to obtain a modified SMS message, wherein modifying the SMS message comprises updating a Transfer Protocol-Protocol Identifier (TP-PID) value of the SMS message; and
transmitting, by the network node, the modified SMS message to the second mobile device.
12 . The method of claim 11 , further comprising:
using a user profile associated with the second mobile device, determining to send the modified SMS message to a spam folder.
13 . The method of claim 11 , wherein the first metadata comprises:
a record of recent messages sent from the first mobile device;
a location of the first mobile device when requesting to deliver the SMS message;
a local time of the second mobile device; and
a messaging history between the first mobile device and the second mobile device.
14 . The method of claim 11 , further comprising:
receiving user input from the second mobile device comprising the SMS message being blocked and reported; and
using the user input, creating a user profile associated with the second mobile device.
15 . The method of claim 11 , further comprising:
receiving user input from the second mobile device comprising the SMS message being blocked and reported;
using the user input, creating a sender profile associated with the first mobile device; and
transmitting the sender profile.
16 . The method of claim 11 , further comprising:
using a mobile application on the second mobile device, displaying the SMS message with a warning notification, wherein the warning notification is based on the TP-PID value.
17 . One or more non-transitory, computer-readable media storing instructions thereon, where the instructions when executed by a network node of a telecommunications network, perform operations for operating the network node, the operations comprising:
receiving, at the network node of the telecommunications network, a request to deliver a Short Message Service (SMS) message from a first mobile device to a second mobile device;
processing first metadata associated with the SMS message to determine a spam likelihood indicator value for the SMS message,
wherein the spam likelihood indicator value is indicative of whether the SMS message is a spam message;
generating, by the network node, a message modification attribute value using the spam likelihood indicator value;
modifying the SMS message using the message modification attribute value to obtain a modified SMS message, wherein modifying the SMS message comprises updating a Transfer Protocol-Protocol Identifier (TP-PID) value of the SMS message; and
transmitting, by the network node, the modified SMS message to the second mobile device.
18 . The one or more non-transitory, computer-readable media of claim 17 , wherein processing the first metadata comprises using a machine learning model to generate a first output comprising a probability of the SMS message being malicious.
19 . The one or more non-transitory, computer-readable media of claim 17 , wherein the TP-PID value comprises:
a first value segment indicating whether the SMS message is malicious;
a second value segment indicating a category of harm associated with the SMS message, if any; and
a third value segment indicating a severity of harm associated with the SMS message, if any.
20 . The one or more non-transitory, computer-readable media of claim 17 , wherein the instructions further cause the network node to perform operations comprising:
using a mobile application on the second mobile device, displaying the SMS message with a warning notification, wherein the warning notification is based on the TP-PID value.