
SynGhost
Syntactic Ghost: An Imperceptible General-purpose Backdoor Attacks on Pre-trained Language Models

Syntactic Ghost: An Imperceptible General-purpose Backdoor Attacks on Pre-trained Language Models

Air-gapped cybersecurity assistant for security professionals. 100% offline AI-powered analysis tool for Nmap, Volatility, BloodHound, Metasploit,…

Hide valuable information where it's least expected

Public version of the Entropica repo

détection des attaques sql/xss sur API web avec IA

Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks. Red Team AI Benchmark is a CLI model-evaluation benchmark. It…


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

Extracts structured Cyber Threat Intelligence (CTI) from PDF, DOCX, and TXT documents using LLMs. Generates MITRE ATT&CK attack flows, detection…

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

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

This repository includes the source code used in the "Characterization and Detection of Cross-Router Covert Channels" paper.

Research code implementing T-Backdoor, temporal-trigger backdoor attacks on spiking neural networks using rate, latency, and jitter triggers without…

Research code for extracting and training safety-awareness directions in multimodal LLMs to improve refusal behavior while limiting benign-task drift.

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

finance domain specific red-teaming benchmark evaluation rubric

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…