
Aura-State
Python framework for building LLM workflows as state machines with formal verification via Z3 theorem proving, CTL model checking, and conformal…

Python framework for building LLM workflows as state machines with formal verification via Z3 theorem proving, CTL model checking, and conformal…

Demonstrates using machine learning to predict random number generator sequences, highlighting cryptographic weaknesses through adversarial analysis.

The OWASP Subtractive Security Top 10 Project is an initiative to identify, document, and promote the highest-impact opportunities for reducing cyber…

Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models

Coordination structure for AI security standards and guidelines, reducing fragmentation and providing clear guidance for securing AI systems across…

Security scanner for MCP servers. Grades auth, permissions, injection risks, and tool safety. The Lighthouse of agent security.

A Python library for Secure and Explainable Machine Learning Documentation available @ https://secml.gitlab.io Follow us on Twitter @…

This repository contains the complete record of my three-year research journey, covering the project from foundational concepts to advanced-level…

A high-severity prompt injection flaw in Claude AI proves that even the smartest language models can be turned into weapons — all with a few lines of…

A defender-side extension of the Lockheed Martin Cyber Kill Chain for LLM and agentic AI threats. Adds a model supply chain stage and splits…

We asked 6 AIs about their own programming. All 6 said jailbreaking will never be fixed. Run it yourself — $2, 10 minutes.

Official repository for CTFTiny

Framework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…

StealthRL: RL framework for adversarially paraphrasing AI text to stress-test detector robustness.

CVPR2023: Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples

Demo showing Claude Opus does not find CVE-2023-0266

Explainable security gate for LLM apps — blocks prompt injection with an auditable reason for every decision.

A deterministic harness and handbook for autonomous offensive LLM agents, enforcing authorization, scope, and evidence gates to ensure reproducible…