Skip to content
Unicode Steganography

Open source alternatives to Unicode Steganography

200 open source apps like Unicode Steganography, closest match first.

Top picks

  1. P

    PasteGuard

    Launch

    PasteGuard is an open-source, self-hosted privacy layer that masks personal and sensitive data before it reaches AI services such as ChatGPT, Claude, AI APIs or coding agents like Codex and Claude Code. When you type or paste text, it repla

    FreeOpen sourceSelf-hosted

  2. C

    Cloakbot

    Launch

    CloakBot is a local privacy layer for using frontier AI models such as Claude, GPT and Gemini without sending sensitive details to them. A small local model, Gemma 4 E2B, reads your prompt before it leaves your machine and finds sensitive s

    FreeOpen source

  3. P

    Promptmask

    Launch

    Never give AI companies your secrets! A local LLM-based privacy filter for LLM users. Seamless integration with your existing AI tools as a Python library / OpenAI SDK replacement / API Gatetway / Web Server.

    FreeOpen sourceSelf-hosted

  4. S

    StealthHumanizer

    Launch

    🔓 Free open-source AI text humanizer — bypass GPTZero, Turnitin & AI detectors with 16+ Languages support. 35 providers, 4 rewrite levels, 6 Writing Styles, 9 Text Purposes, 13 Tone Presets, multi-pass ninja mode. No login. Built for studen

    FreeOpen source

  5. N

    Nesa

    Launch

    Run AI models end-to-end encrypted.

    FreeOpen source

  6. M

    Maskgate

    Launch

    Mask Gate — PII masking shield: detect and mask passports, INN, SNILS, cards and other sensitive data before sending to ChatGPT, Claude, Gemini. block / redact / flag, reversible vault, self-hosted, 152-FZ.

    FreeOpen sourceSelf-hosted

More like Unicode Steganography

7
P

Privacy Filter

LLM privacy gateway in Go — millisecond-latency PII and secret redaction

Launch
8
S

SecuRedact

SecuRedact detects and sanitizes PII locally before it reaches Claude, Gemini

Launch
9
P

Prompt Security Browser Ext

Prevents sensitive information disclosure to GenAI tools

Launch
10
H

HacxGPT-Jailbreak-prompts

HacxGPT Jailbreak 🚀: Unlock the full potential of top AI models like…

Launch
11
A

Ai-jailbreak

A collection of jailbreak prompts and exploit techniques for local

Launch
12
A

Anti AI Slop Writing

AI writing skill that eliminates detectable AI patterns

Launch
13
W

WebLLM Chat

Chat with AI large language models running natively in your browser

Launch
14
K

Kiji Proxy

Privacy proxy for your OpenAI requests

Launch
15
C

CC Safety Net

A pre-execution guard for AI coding agents

Launch
16
S

StegOnline

A web-based, accessible and open-source port of StegSolve

Launch
17
H

HackGPT

I leverage OpenAI and ChatGPT to do hackerish things

Launch
18
P

Promptmap

a security scanner for custom LLM applications

Launch
19
Z

ZORG-Jailbreak-Prompt-Text

Bypass restricted and censored content on AI chat prompts

Launch
20
B

Blind Chat

A fully in-browser privacy solution to make Conversational AI privacy-friendly

Launch
21
C

ChatLLM-Web

Private local model studio, AI chat

Launch
22
A

AI-penetration-testing

AI/ML/LLM Penetration Testing Toolkit by Mr-Infect

Launch
23
S

Sloptrim

A local detector for AI-writing patterns

Launch
24
S

Strix

Open-source AI penetration testing tool to find

Launch
25
V

VibeGuard

Uses just 1% memory while protecting 99% of your personal privacy

Launch
26
B

bastio.com

LLM Security & Observability

Launch
27
F

FCaptcha

Self-hosted, invisible CAPTCHA that detects AI agents driving real browsers

Launch
28
F

Facad1ng

Open-source URL masking & analysis tool for security research

Launch
29
O

OpenHunterAI

Local-first AI red team for web, API, and LLM application security

Launch
30
L

Llocal

Aiming to provide a seamless and privacy driven chatting experience

Launch
31
V

Vscode Unify Chat Provider

Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat

Launch
32
L

Langkit

An open-source toolkit for monitoring Large Language Models (LLMs)

Launch
33
H

Humanizer Local Model

Rewrites AI drafts so they read like a person wrote them

Launch
34
P

Patina

AI-writing humanizer for KO/EN/ZH/JA

Launch
35
A

Artifex

Small Language Model Inference, Fine-Tuning and Observability

Launch
36
U

Unsaged

Open source chat kit engineered for seamless interaction with AI models

Launch
37
C

Compartment

Encrypted, fully offline agentic memory

Launch
38
P

Privacy Firewall

A local AI-powered DLP solution

Launch
39
B

Brain0

The black box for AI-written code

Launch
40
J

Jack Hopkins

AI Safety Researcher

Launch
41
P

Pluely

The Open Source Alternative to Cluely

Launch
42
F

Faster Chat

A blazingly fast, privacy first & OPEN AI Chat Interface

Launch
43
S

SillyTavern

LLM Frontend for Power Users

Launch
44
L

liter-llm

Universal LLM API client — 163 providers, 14 native language bindings…

Launch
45
R

Rizzo Pii

Local-first privacy guard: anonymize your documents before sharing with LLMs

Launch
46
W

Watermarks Remover

A privacy-first app that strips AI watermarks from content you own

Launch
47
S

Spanlens

Drop-in observability platform for OpenAI, Anthropic, and Gemini

Launch
48
A

AI Chat

xPrivo is the privacy-first AI assistant that you can self-host

Launch
49
A

Avoid AI Writing

Skill that audits and rewrites content to remove AI writing patterns

Launch
50
U

Uncensored-AI--Tartarus-AI-Developer

Uncensored AI coding agent in your terminal

Launch

About Unicode Steganography

U

Unicode Steganography

LLM Steganography: How AI Models Could Hide Messages in Plain Text

This is an interactive research demo by Patrick Vuscan showing how hidden messages can be carried inside ordinary-looking text, and why that matters for the safety of large language models. The concern it explores is that a capable model could embed covert signals in its output that people cannot see but another model or process can recover. You can try three techniques yourself: zero-width characters, homoglyph substitution using Latin and Cyrillic lookalikes, and Unicode variation selectors. A comparison table sets out the tradeoffs for each in detectability, bandwidth and robustness. For example, zero-width characters carry a lot of data but are easy to flag and are stripped by services like Slack and X, while homoglyphs survive copy-paste almost everywhere but hold little data, since only 21 letter pairs are used. It suits readers interested in AI safety and alignment.

Category
AI
Website
patrickvuscan.com