nethical6/conversation-steganography

Health v2 · maintenance only

Flags: no_releases young

Adoption not part of the score

1239 stars · 89 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Go CLI tool that hides encrypted secret messages inside natural-looking chat text generated by a local LLM (GPT-2), enabling covert communication over any messaging app. It is an educational proof of concept that encrypts messages locally and disguises them as innocent cover text that a recipient can decode.

Use cases

• hide secret messages inside normal-looking chat conversations
• send covert messages over WhatsApp or Telegram without detection
• exchange encrypted messages that look like innocent small talk
• experiment with LLM-based text steganography
• simulate two-party covert communication locally
• research steganography detection of AI-generated cover text

When to choose

• you need plausible-deniability messaging that doesn't look encrypted to observers
• you want a local, offline steganography tool with no cloud dependency
• you're researching or learning about LLM-based steganography techniques

When to avoid

• you need production-grade security - it's a proof of concept with known weaknesses
• you require strong protection against steganalysis, which is actively being developed
• you want a polished GUI or mobile app rather than a CLI
• your use case involves any illegal activity - it's for educational and research purposes only

Facets

cli-tool · maturity experimental

cryptography nlp llm-inference security cli privacy security large-language-models censorship-circumvention windows cli cross-platform steganography llm-steganography covert-communication gpt-2 proof-of-concept encrypted-messaging natural-language-processing linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="nethical6/conversation-steganography")