
FARO
FARO - Document Sensitivity Detector

FARO - Document Sensitivity Detector

Official code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing

A benchmark for evaluating AI agents on fixing real-world security vulnerabilities.

A serverless networking protocol designed for resilient state synchronization between autonomous agents in fragmented, low-bandwidth networks

This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.


Inference scaling for LLM safety assurance

Production AI defense with 7-layer protection: mathematical constraints, object-capability access, distributed O2 consensus, SVETILO ethics. First…

Voice-based detective interrogation game. Mistral Large 3 + Voxtral STT + ElevenLabs TTS. Built for the Mistral Worldwide Hackathon 2026.

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

ML-based detection of Zombie ZIP archive header evasion attacks (CVE-2026-0866)

Prohibited Items Segmentation via Occlusion-aware Bilayer Modeling (ICME 2025)

Public version of the Entropica repo

A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.

CLPSTNet: A Progressive Multi-Scale Convolutional Steganography Model Integrating Curriculum Learning

AGLS

détection des attaques sql/xss sur API web avec IA

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