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

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

Image-based Android malware detection framework tackling obfuscation and concept drift. Includes curated datasets and Python code for training…

This project (PoC for now, and part of Shit Bucket) involves face detection, face recognition and adversarial input to protect avatars

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

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

Multi-agent automated context management for long horizon tasks in local AI Agents

Memory-free continual learning framework for malware classification using mode connectivity-based interpolation. Supports class-incremental and…

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

Implements machine and deep learning methods for indoor UWB jammer localization, including hyperparameter optimization, classification, and…

Evaluation framework for AI penetration testing agents that measures validated vulnerability discovery using LLM-based semantic matching, bipartite…

Java SDK for building analytics pipelines that process and enrich unstructured text data with annotations, type systems, and modular analysis engines.

Benchmark suite and code for detecting AI alignment failures, with 44 benchmarks across ten failure types and a zero-shot RLCD detector evaluated on…

Benchmarking prompt injection detections for web agents.

Privacy testing library for deep learning systems, enabling assessment of susceptibility to membership inference, model extraction, and model…

End-to-end Python framework for time series intelligence, offering anomaly detection, forecasting, change point detection, AutoML, ensembles, and…


A privacy-first app that strips AI watermarks from content you own.

Automatic extraction of relevant features from time series: