
BrokenHill
A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)


Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

Cyber Threat Defense World Modeling

Detection of rootkit file hiding activities through analysis of shifts in kernel function execution times.

Provably secure linguistic steganography embedding secret messages into LLM-generated text via rotation range-coding. Includes embed, extract, and…

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

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

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

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


Structured challenge repository offering bounties for breaking a neural-network-based random number generator validated against NIST SP 800-22 and SP…

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

Open-source OCR engine with LSTM neural network models for extracting text from images and scanned documents in 100+ languages via CLI, C/C++…

Deep learning framework for object detection, segmentation, classification, pose estimation, and tracking using pre-trained YOLO models and…

A python library for user-friendly forecasting and anomaly detection on time series.