Tools

owasp/owasp-model-card-security-standard

Open standard for documenting security-relevant metadata of AI models, including training data provenance, PII risk, known vulnerabilities, and…

toxy4ny/delirium-ai-safety-benchmark

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

owasp/damn-vulnerable-ml-model

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

artur-augustyniak/class_struggle

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

afbf4c8996f/jammer-loc

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

soildworks/agentic-clip-benchmark

An automated, high-precision zero-shot evaluation pipeline for OpenAI's CLIP model on CIFAR-10. Features 88.80% accuracy, Safetensors security…

skac44/cve-2024-38063

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

jd0965199-oss/ethibench

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

yadavmukesh/log4shell-vulnerability-cve-2021-44228-

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

shoucheng3/apache__uima-uimaj_cve-2022-32287_3-3-0

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

ghostwolflab/ai_security_top

A structured knowledge base covering AI security fundamentals, threat modeling, red team offensive techniques, and blue team defenses, including LLM…

mlily2024/final-project-sql-injection-pipeline

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

qkrrkd90-source/weavemark

Reference implementation of a multi-bit LLM watermarking scheme using coded payload spreading, unbiased reweighting, and soft-decision ECC decoding…

cucu220123/safety-awareness

Research code for extracting and training safety-awareness directions in multimodal LLMs to improve refusal behavior while limiting benign-task drift.