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

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

A collection of awesome resources related AI security

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

Curated, community-maintained directory of data broker opt-out instructions to help individuals remove personal information from people-search sites…

CVE-2026-6765, Test only FormAutofill handlers exposed in Firefox

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

Browser PoC demonstrating CVE-2026-2828, a WebGPU timing side-channel that leaks cross-origin iframe pixel values by measuring GPU timestamp-query…

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal…

The Security Toolkit for LLM Interactions

Practical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.

Improve your security and privacy by blocking ads, tracking and malware domains.

Python library for adversarial machine learning security, enabling red and blue teams to run evasion, poisoning, extraction, and inference attacks…

The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)

Never ever ever use pixelation as a redaction technique

Mobile camera-based application that attempts to alter photos to preserve their utility to humans while making them unusable for facial recognition…

Privaxy is the next generation tracker and advertisement blocker. It blocks ads and trackers by MITMing HTTP(s) traffic. Also check out my new…


This project (PoC for now, and part of Shit Bucket) involves face detection, face recognition and adversarial input to protect avatars