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

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

A next-generation multi-echelon anti-ransomware fortress for Windows, combining hypervisor, eBPF, AI deception, and hardware-enforced security.

The code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

FLNET2023 is a dataset designed for intrusion detection in Federated Learning scenarios. It's built using the CORE emulator, simulating a realistic…

Research repository documenting LLM generalization ceilings in code security vulnerability detection, with cross-evaluation across synthetic and…

Research toolkit for analyzing AI agent behavioral patterns through multi-disciplinary corpus analysis. Parses session logs, runs 23 analytical…

A curated portfolio showcasing my SOC investigations, threat hunting projects, DFIR labs, detection engineering, technical blogs, and cybersecurity…

détection des attaques sql/xss sur API web avec IA


Code for ACL 2026 (main) paper "DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation"

An implementation of the FAIR CRQ Framework

Public version of the Entropica repo

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

Open standard for documenting security-relevant metadata of AI models, including training data provenance, PII risk, known vulnerabilities, and…

Ensemble framework for software vulnerability detection and repair using multiple large language models, with consensus analysis and evaluation tools…

Intentionally vulnerable machine learning model for hands-on security training. Explore common ML vulnerabilities, adversarial attacks, and defensive…

Autoencoder-based anomaly detection for identifying phishing domains using CERT Polska warning list data, with Jupyter notebooks for research and…

Structured challenge repository offering bounties for breaking a neural-network-based random number generator validated against NIST SP 800-22 and SP…