Collaborative Content Masking for Sensitive Screen Sharing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current video conferencing techniques lack effective methods for enhancing collaboration and interaction by masking sensitive content during content sharing among multiple attendees.
Innovation Solution
A machine-learned model is employed to identify sensitive content within shared content streams, generating masks to conceal such information from display, thereby allowing only non-sensitive content to be visible to other participants.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If content sharing is enabled in video conferencing, then collaboration and interaction between attendees are enhanced, but sensitive information may be exposed to unauthorized participants
Solution Approach 1:
A machine-learned model is introduced as an intermediary between the content source and display devices. The model receives content streams, automatically identifies sensitive regions through image analysis, and generates masks that selectively obscure sensitive information while preserving non-sensitive content for sharing among participants.
Solution Approach 2:
The sensitive content is extracted and separated from the overall content stream through automated detection. The machine-learned model identifies and isolates sensitive regions (such as personal information, confidential data, or private communications) and removes them via masking, allowing the remaining non-sensitive content to be shared safely.
2Reliability
If manual content review is performed to mask sensitive information, then privacy protection is improved, but computing resources and time are consumed
Solution Approach 1:
The system performs self-service by automatically detecting and masking sensitive content without requiring manual review. The machine-learned model autonomously analyzes content streams in real-time, identifies sensitive regions, and applies appropriate masking, eliminating the need for human intervention while maintaining privacy protection.
Solution Approach 2:
The manual mechanical process of content review is replaced with an automated machine-learned system. The model uses image processing and pattern recognition algorithms to automatically identify sensitive content, substituting human computational effort with automated computational processes that are more efficient and scalable.
3Measurement precision
If automated content analysis is implemented, then sensitive content identification accuracy is improved, but device complexity increases
Solution Approach 1:
The machine-learned model serves multiple functions within a single integrated system: it performs image analysis, sensitive content detection, region identification, and mask generation. This multi-functional approach consolidates what would otherwise require separate systems into one unified solution, managing complexity while maintaining high detection accuracy.
Data Source
AI summary
A machine-learned sharing system and methods are provided for sharing content with users while masking sensitive information. The system receives a content stream for display to one or more users, converts the content stream into image data representative of at least a portion of the content stream, inputs the image data into a machine-learned model configured for masking sensitive content within shared content, receives from the machine-learned model a first mask indicative of a region within the first content stream that contains sensitive content, and renders a display of the content stream that masks the sensitive content based at least in part on the first mask indicative of the region of the first content stream having the sensitive content.