
scan
0-day malware detection for binaries, source & scripts (that doesn't suck)

0-day malware detection for binaries, source & scripts (that doesn't suck)

Proof-of-concept that poisons MLflow registered models via the REST API, embedding a malicious pickle to trigger RCE when the model is loaded.


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

Hybrid machine-learning pipelines for detecting SQL injection in web traffic, combining DistilBERT and BERT-GNN models with adversarial training and…

This repository hosts a multimodal web attack dataset (MWAD) to advance AI-driven threat detection research.

An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Retrieval-Augmented Generation Systems.

Asymmetric defense against adversarial AI agents. VeilGate evaluates each incoming request, redirects suspected agents into a per-IP-consistent…

AI Code Security — four agents that catch what SAST misses in AI-generated code. Built on GitLab Duo Agent Platform.

LLM powered fuzzing via OSS-Fuzz.

détection des attaques sql/xss sur API web avec IA

Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models

A guided mutation-based fuzzer for ML-based Web Application Firewalls

Restructured and Collaborated SIEM and CVSS Infrastructure. Presented at Blackhat Asia Arsenal 2020.