
claude-awm
Evades LLM text watermarks by injecting Unicode variation selectors; includes the SynthID generator, mean-g detector, normalization defenses, and…

Evades LLM text watermarks by injecting Unicode variation selectors; includes the SynthID generator, mean-g detector, normalization defenses, and…

Research-only AI watermark robustness toolkit: local reverse proxy strips C2PA/EXIF/XMP, Unicode, image/audio stego, OOXML/PDF metadata, and scans…

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

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

Implementation of optimal coupling-based distortion-free text watermarking to embed detectable signals in LLM-generated text while preserving quality.

[ICCV 2025] Anti-Tamper Protection for Unauthorized Individual Image Generation

Provably secure linguistic steganography embedding secret messages into LLM-generated text via rotation range-coding. Includes embed, extract, and…

Advanced EDR Evasion via AI Telemetry Spoofing & WASM Sandboxing. Project Onyx is a PoC Red Team pipeline designed to demonstrate advanced evasion…

File Injector is a script that allows you to store any file in an image using steganography

reverse engineering SynthID for text

Automated steganography detection tool that scans websites, web servers, and local directories using AI-driven object/text recognition and deep file…

reverse engineering Gemini's SynthID detection

AI-driven automated threat analysis pipeline that routes files, URLs, IPs, domains, or images through specialized security analyzers and generates…

Image Payload Creating/Injecting tools

Free hands-on digital forensics labs for students and faculty

Curated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…
