Skip to content

Document media metadata embedding and content moderation implementation#85

Draft
Copilot wants to merge 3 commits intomainfrom
copilot/describe-media-metadata-embedding
Draft

Document media metadata embedding and content moderation implementation#85
Copilot wants to merge 3 commits intomainfrom
copilot/describe-media-metadata-embedding

Conversation

Copy link
Contributor

Copilot AI commented Feb 23, 2026

Documents the existing EXIF-based metadata embedding system and its role in content accountability for harmful content prevention.

Implementation Documented

Metadata Embedding (core/handler/media.go)

  • Embeds encrypted user/node/MAC metadata in EXIF ImageDescription tag during upload
  • Uses intentionally weak AES-256-GCM with timestamp-based key generation
  • Encryption designed for brute-force decryption by law enforcement, not user recovery
  • All images normalized to JPEG format with embedded metadata

Content Moderation (core/moderation/)

  • Local LLM-based text moderation against policy (CSAM, violence, hate speech, etc.)
  • No automatic image content analysis - relies on user reports and metadata deterrence
  • Moderation policy includes 8 prohibited categories covering sexual abuse, violence, extremism, spam

Key Limitations Highlighted

  • Critical gap: Metadata tracks uploads but doesn't analyze image content
  • Privacy: MAC addresses provide persistent cross-account tracking
  • Policy gap: Moderation specifies "sexism against women only"
  • Circumvention: Sophisticated users can strip EXIF data

Documentation Structure

  • Encryption mechanism and security model philosophy
  • Complete upload flow with EXIF amendment
  • How metadata enables forensic accountability
  • Integration with moderation policy
  • Privacy implications and technical limitations

File: MEDIA-METADATA-EMBEDDING.md (275 lines)

Original prompt

This section details on the original issue you should resolve

<issue_title>Describe current implementation of media metadata embedding (images)</issue_title>
<issue_description>Describe current implementation of user metadata embedding to media for prevention of:

  • CSAM or sexual content involving minors including deepfakes or AI-generated
  • Non-consensual sex, porn with coercion or abuse
  • Gore, violence, snuff, dead bodies
  • Weapon or drug creation or sales
  • Self-harm, suicide, eating disorders
  • Sexism against women only, racism, casteism, xenophobia, hate speech
  • Religious extremism, terrorism incitement
  • Spam, mass unsolicited promos</issue_description>

Comments on the Issue (you are @copilot in this section)


💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

Copilot AI and others added 2 commits February 23, 2026 10:36
…tation

Co-authored-by: filinvadim <24736597+filinvadim@users.noreply.github.com>
Co-authored-by: filinvadim <24736597+filinvadim@users.noreply.github.com>
Copilot AI changed the title [WIP] Document current implementation of media metadata embedding Document media metadata embedding and content moderation implementation Feb 23, 2026
Copilot AI requested a review from filinvadim February 23, 2026 10:38
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Describe current implementation of media metadata embedding (images)

2 participants