BEHAVIOR-BASED DETECTION OF AUTOMATED SCANNER EVENTS

Organization Name

Inventor(s)

BEHAVIOR-BASED DETECTION OF AUTOMATED SCANNER EVENTS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240296104 titled 'BEHAVIOR-BASED DETECTION OF AUTOMATED SCANNER EVENTS

The abstract describes a method where an application server or another device analyzes input data related to an activity involving an electronic communication message to determine the probability that the activity is associated with an automated scanner.

An application server receives input data related to an activity involving an electronic communication message.
The server identifies features associated with the activity and source network addresses of known automated scanners.
The features and source network addresses are input into a positive-and-unlabeled learning model.
The learning model outputs a classification result indicating the probability that the activity is linked to an automated scanner.

Potential Applications: - Email marketing campaigns to identify and filter out automated scanners. - Enhancing cybersecurity measures by detecting potential threats in electronic communication activities.

Problems Solved: - Efficient identification of automated scanners in electronic communication activities. - Improved security measures to protect against malicious automated scanning activities.

Benefits: - Enhanced cybersecurity by identifying potential threats in real-time. - Increased efficiency in filtering out automated scanners from legitimate activities.

Commercial Applications: Title: "Automated Scanner Detection System for Email Marketing Campaigns" This technology can be utilized by email marketing companies to enhance the security of their campaigns and protect against automated scanning activities. It can also be integrated into cybersecurity systems to improve threat detection capabilities in electronic communication networks.

Questions about the technology: 1. How does the positive-and-unlabeled learning model improve the detection of automated scanners in electronic communication activities? 2. What are the potential implications of false positives or false negatives in the classification results of the learning model?

Original Abstract Submitted

methods, systems, apparatuses, devices, and computer program products are described. an application server or another device may receive a set of input data associated with an activity between an actor and an electronic communication message (e.g., a marketing email). from the input data, the application server may identify a set of features associated with the activity (an open rate, a click rate, etc.) and a set of source network addresses of respective, known automated scanners. the application server may input the features and source network addresses into a positive-and-unlabeled (pu) learning model, which may output a classification result that indicates a probability that the activity is associated with an automated scanner.