A community-run reference for state-of-the-art adversarial example defenses.

We help to create the foundations of reliable and trustworthy AI systems.

Qwiet AI secures applications with AI-powered code analysis, natural language insights, and context-aware findings - built to empower developers and protect your software supply chain.

# Deep Learning | Interpretability # Deep Learning | Out-of-Distribution Detection | Adversarial Robustness # Deep Learning | Testing ML | Adversarial Robustness · deep, learning, adversarial, robustness, interpretability

Transform your AI models into safe and valuable assets. Secure your on-device AI models against reverse engineering with a low computing footprint. Protect your competitive edge and technological advance. Deploy, manage… · models, against, protect, award, europe

Verifiably private Inference API Develop AI products without worrying about security, privacy, or compliance We take financial responsibility for any breach or misuse · verifiably, private, security, privacy, take

Pioneering research in AI security and safety. Building robust systems that ensure responsible development and deployment of artificial intelligence. Our research spans multiple critical areas in AI security and safety… · systems, security, research, safety, robust

Discover BlindAI: Open-source AI privacy via Trusted Execution Environments and Python for secure model querying.

The explosion of interest in machine learning coupled with the increasing availability of large amounts of data and tools for simple development of models has quickly led to an avalanche of examples of hurtful, unsafe or… · models, data, tools, examples, model

Immediate ROI with a no Capex, all-inclusive solution. Zero infrastructure changes required and rapid deployment. Start small and easily scale up as successful milestones are hit. Seamlessly switch between workflows as… · immediate, roi, capex, inclusive, solution

Effortlessly manage your model training and inference pipelines and streamline your ML operations with our state-of-the-art, end-to-end ML-Ops platform. Rest assured knowing that our AI solutions are built with a strong… · end, effortlessly, manage, model, training

Progress in AI over the last decade has been accompanied by a lack of robustness, rooted in a predictability crisis: highly-accurate image classifiers fail on images with an unusual background, robots surprise us with unanticipated reward hacking phenomena, and powerful language models display

Virtual worlds for solving real problems. Digital twin simulation that drives safe, predictable, and resilient smart systems

AI EdgeLabs - The most powerful AI cybersecurity tool

This web page contains materials to accompany the NeurIPS 2018 tutorial, "Adversarial Robustness: Theory and Practice", by Zico Kolter and Aleksander Madry. The notes are in **very early draft form**, and we will be updating them (organizing material more, writing them in a more consistent form with the relevant citations,...

The universal network for decentralized AI infrastructure; delivering secure interoperability, scalable and customizable consensus, and privacy-preserving peer-to-peer networks for data indexing and exchange, compute… · infrastructure, scalable, peer, compute, developers

Das Fraunhofer IKS ist Ihr Partner bei der Entwicklung innovativer Software-Ansätze für die Bereiche Industrie 4.0 und autonomes Fahren.

Examples of AI Improving AI

The Safe and Trusted AI PhD programme focusses on the use of symbolic AI techniques for ensuring the safety and trustworthiness of AI systems. The Centre’s direction, training and supervision is delivered by a team of… · training, centre, techniques, safe, symbolic

delivering a seamless, industry-optimized API for AI trust, ensuring business alignment and ethical integrity across all AI models

Empower your AI with transparency, security, and efficiency. Eliminate black-box uncertainties, reduce risks, harden models against attacks, and deploy confidently with dynamic testing, backdoor detection, and privacy-first tools. Take control today.

We deliver mission critical insights by uncovering hidden relationships.

RobustifAI aims to develop a rigorous design and deployment methodology tailored for reliable, robust and trustworthy Generative Artificial Intelligence (GenAI).

Where Emerging Threats Meet Expert Analysis

The Trusted Leader in Edge-to-Edge Cybersecurity Visibility and Response

Leading AI governance platform for enterprise compliance and responsible AI deployment. Automate EU AI Act compliance and risk management.

Stakeholders Advocating for Fair and Ethical AI in Interpreting

Transform your AI approach by enabling organizations to deploy reliable and responsible AI agents that work with your data

Software framework for runtime-Adaptive and secure deep Learning On Heterogeneous Architectures

Sparking the next generation of AI Products

Sensing, ArtiFicial intelligence, and Edge networking towards Rural Health monitoring. Sensing, ArtiFicial intelligence, and Edge networking towards Rural Health monitoring. Focuses on setting up a pilot project to… · health, rural, monitoring, sensing, artificial

A comprehensive suite of capabilities to find, monitor and mitigate AI Model issues Scan, Spot, and Soften adversarial attacks and thoroughly understand your AI/ML models’ vulnerabilities. Quantitatively measure the… · monitor, models, measure, comprehensive, mitigate

[Proposal] About This Workshop As data and computing infrastructures become increasingly abundant, machine learning (ML) systems are applied to ever more problems. However, for safety-critical domains, their high performance alone is not enough: applications like autonomous driving, robotics

Making society more resilient by using human understanding, state-of-the-art technology (eBPF, Webassembly and AI) and empirical methods for achievable threat-informed cloud security - 100% independent - 100% reality… · using, 100, github, com, k8sstormcenter

AI Engineering als Enabler für eine fundierte Sicherheitsargumentation über den gesamten Lebenszyklus einer KI-Funktion.

Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems.

Adversarial Robustness Toolbox is an LF AI & Data Foundation Project Adversarial Robustness Toolbox (ART) provides tools that enable developers and researchers to evaluate, defend, and verify Machine Learning models and… · art, modules, adversarial, machine, learning

The overarching aim of the Safe Artificial Intelligence Lab is to develop novel computational methods and tools for providing safety guarantees to a wide range of autonomous systems, including autonomous vehicles… · safe, systems, artificial, intelligence, autonomous

The Learning in Verification group (LiVe Lab) focuses on the interactions of machine learning and verification. Our research includes Explainable AI, Verification of Neural Networks, Stochastic Games and Control… · verification, learning, neural, networks, ltl

Trusted Autonomy, Data Analytics, Autonomous Analytics, Decision Analytics, Big Data, Autonomous Systems, Trust, Autonomy, Artificial Intelligence, Cognitive Cyber Symbiosis

Health & safety, operational efficiency and risk mitigation using cutting edge AI and CCTV

TruthfulAI: Building reliable and trustworthy AI systems for the future.

Center for Explainable Responsible and Theory-driven Artificial Intelligence More information about CERTAIN Learn more