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

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

This repository contains the complete record of my three-year research journey, covering the project from foundational concepts to advanced-level…

Ghostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack

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

Sec-Gemini is a cutting-edge AI model designed to enhance cybersecurity capabilities and empower defenders in the ongoing battle against cyber…

PISIGuard runs entirely in your browser. It spots names, email addresses, phone numbers, credit card numbers, passwords, API keys, and more, replaces…

PoC code from DEF CON 25 presentation


Scan LLM outputs and AI-generated content for data exfiltration signals (EchoLeak, CVE-2025-32711) before they reach users or downstream systems

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

OpenAnt from Knostic is the leading open source LLM-based vulnerability discovery product, helping defenders proactively find verified security flaws…

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

Official repository for CTFTiny

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

Security benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…