
HydraDragonAV-Mobile
Android Antivirus which doesn't require root, adb, ca install and cloud with many features and ways to detect more zero-day malware

Android Antivirus which doesn't require root, adb, ca install and cloud with many features and ways to detect more zero-day malware

Advanced detection of port scanning, DoS and malware attacks using Machine Learning techniques

Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…

Evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…

This repository contains the official implementation of the paper "[Safety in Batches? Understanding and Mitigating Safety Failures in Batch…

LLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…

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

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.

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

Streamlit-based insider threat detection prototype using XGBoost and Isolation Forest to analyze employee activity data, generate risk summaries, and…

CERTITUDE - A python package to classify URLs as malicious or benign

Simulates CVE-2024-38063 TCP/IP remote code execution attack, captures network traffic with TShark, and trains a machine learning model to detect…

This repository provides an in-depth analysis of the Log4Shell vulnerability (CVE-2021-44228) and implements a machine learning-based approach to…

finance domain specific red-teaming benchmark evaluation rubric

Next-generation JavaScript identifier recovery with LLMs.

3D Passive Face Liveness Detection (Anti-Spoofing) & Deepfake detection. A single image is needed to compute liveness score. 99,67% accuracy on our…