
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…

Strip multi-vendor AI provenance marks: Unicode text hygiene, statistical rewrite hooks, and C2PA/metadata from PNG/JPEG/SVG/PDF/DOCX/HTML/MD

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

Writeup for the DEF CON 30 badge challenge

A payload delivery system which embeds payloads in an executable's icon file!

This repository is a collection of powershell functions every hacker should know

Psychological warfare in reverse engineering

Psychological warfare in reverse engineering

A Repository to Track Anti-Forensic Techniques

RunPE implementation with multiple evasive techniques (2)

An OSINT / digital forensics tool built in Python

Embed a payload inside a PNG file

Exfiltrate data over screen interfaces

Digital Forensics Intelligence Framework


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