User Input Analysis for APT Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Advanced Persistent Threats (APTs) are difficult to detect as they mimic legitimate user behavior, making it challenging for system administrators to distinguish between malicious and non-malicious activities in network and computing resources.

Innovation Solution

A computer-implemented method using user-input information to identify security threats by detecting activity, determining if user input was provided during the activity, and performing security actions based on the determination of potential threats, including analyzing user input patterns and device usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional security detection methods are used, then detection simplicity is maintained, but detection accuracy deteriorates because APTs mimic legitimate user behavior

Engineering Contradiction:
Improvedetection accuracyVSAvoiddetection system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by establishing baseline user behavior patterns before actual security detection occurs. It collects and analyzes user input data, device usage patterns, and application behavior over time to create reference profiles. When security events occur, the system compares them against these pre-established baselines, enabling accurate detection of APTs that mimic legitimate behavior without requiring complex real-time analysis.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If user input monitoring is implemented, then detection accuracy improves, but ease of operation deteriorates due to additional user interaction requirements

Engineering Contradiction:
Improvethreat identification accuracyVSAvoidsystem operation simplicity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system implements self-service by automatically collecting user input data through background processes and device drivers without requiring user awareness or participation. The security software autonomously monitors keyboard inputs, mouse movements, and application usage patterns, then processes this data to establish behavior baselines and detect threats. This eliminates the need for user training or manual configuration while maintaining high detection accuracy.

Inventive Principle:
Principle #25Self-service

3Reliability

If comprehensive activity monitoring is performed, then security detection capability improves, but loss of time increases due to extensive data analysis

Engineering Contradiction:
Improvesecurity detection reliabilityVSAvoidanalysis time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system extracts and monitors only the most critical security-relevant parameters from user behavior, such as input timing patterns, device usage frequency, and application launch sequences. By focusing on these key indicators rather than analyzing all possible user actions, the system maintains high detection reliability while minimizing data processing time and computational overhead.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS9166995B1Systems and methods for using user-input information to identify computer security threats
Publication Date: 2015.10.20 GEN DIGITAL INC
  • US9166995B1 patent drawing
  • US9166995B1 patent drawing
  • US9166995B1 patent drawing

AI summary

A computer-implemented method for using user-input information to identify computer security threats may include (1) detecting activity at a computing system, (2) determining whether a user provided input at the computing system when the activity occurred, (3) determining that the activity indicates a potential security threat based at least in part on whether the user provided input at the computing system when the activity occurred, and (4) performing a security action on the activity in response to the determination that the activity indicates a potential security threat. Various other methods, systems, and computer-readable media are also disclosed.