ATLAS (Adversarial Threat Landscape for Artificial-Intelligence Systems) is a globally accessible, living knowledge base of adversary tactics and techniques against Al-enabled systems based on real-world attack observations and realistic demonstrations from Al red teams and security groups.

Risk Atlas Nexus provides tooling to connect fragmented AI governance resources through a community-driven approach to curation of linkages between risks, datasets, benchmarks, and mitigations. It transforms abstract risk definitions into actionable AI governance workflows.

An artificial intelligence (AI) impact assessment tool to provide organisations a method to assess AI systems for compliance with Canadian human rights law. The purpose of this human rights AI impact assessment is to assist developers and administrators of AI systems to identify, assess, minimise or avoid discrimination and uphold human rights obligations throughout the lifecycle of an AI system.

This tool provides a comprehensive risk management framework for frontier AI development, integrating established risk management principles with AI-specific practices. It combines four key components: risk identification through systematic methods, quantitative risk analysis, targeted risk treatment measures, and clear governance structures.

Behavior Elicitation Tool (BET) is a complex-AI system that systematically probes and elicits specific behaviors from cutting-edge LLMs. Whether for red-teaming or targeted behavioral analysis, this automated solution is Dynamic Optimized and Adversarial (DAO) and can be configured to test the robustness precisely and help to have a better control of the AI system.

COMPL-AI is an open-source compliance-centered evaluation framework for Generative AI models

This document addresses how artificial intelligence machine learning can impact the safety of machinery and machinery systems.

AIxploit is a tool designed to evaluate and enhance the robustness of Large Language Models (LLMs) through adversarial testing. This tool simulates various attack scenarios to identify vulnerabilities and weaknesses in LLMs, ensuring they are more resilient and reliable in real-world applications.

The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in their generative AI systems.

Trustworthy AI Procurement CardTM is a non-exhaustive list of information which can accompany acquisition decisions. The Card is similar to the DataSheets or Model Cards, in the sense that the objective is to promote transparency and better due diligence during AI procurement process.

garak, Generative AI Red-teaming & Assessment Kit, is an LLM vulnerability scanner. Garak checks if an LLM can be made to fail.

Harms Modeling is a practice designed to help you anticipate the potential for harm, identify gaps in product that could put people at risk, and ultimately create approaches that proactively address harm.

Dioptra is an open source software test platform for assessing the trustworthy characteristics of artificial intelligence (AI). It helps developers on determining which types of attacks may impact negatively their model's performance.

Evaluate input-output safeguards for LLM systems such as jailbreak and hallucination detectors, to understand how good they are and on which type of inputs they fail.

AI Security Platform for GenAI and Conversational AI applications. Probe enables security officers and developers identify, mitigate, and monitor AI system security.

Responsible AI (RAI) Repairing Assistant

This document reviews current aerospace software, hardware, and system development standards used in the certification/approval process of safety-critical airborne and ground-based systems, and assesses whether these standards are compatible with a typical Artificial Intelligence (AI) and Machine Learning (ML) development approach.

First full revision of PAS 1881:2020 to reflect learning from recent automated vehicle trials and input from stakeholders. It deals with how to build operational safety cases for trialling and testing of AVs so that ultimately connected and automated vehicles can be deployed safely, and the public will be confident about their safety.

PAS 11281 is the international standard on road vehicles that gives recommendations for managing security risks that might lead to a compromise of safety in a connected automotive ecosystem.

The scope of the expert recommendation is the design and layout of autonomous systems from the perspective of human reliability.