
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

Customer Assurance Operating System. Answer the security questionnaires your customers send you, once.

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

For our CCS24 paper 🏆 "ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries" by Danning Xie, Zhuo Zhang, Nan…

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

PoC code from DEF CON 25 presentation

Machine-learn password mangling rules


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

QuantumLock is an open-source, quantum-resistant Bitcoin protocol designed to protect digital assets from future quantum computing threats. Featuring…


Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

Reverse of OpenAI Privacy Filter: same 1.5B model, returns PII as structured spans instead of masking.

This repository demonstrates a machine learning pipeline for detecting MITRE ATT&CK techniques from logs and enriching the output using a local LLM.

Research related to the Power Tracks discovered in market microstructure.