In this paper, we take a first step towards answering the question of how to design fair machine learning algorithms that are robust to adversarial attacks. Using a minimax framework, we aim to design an adversarially robust fair regression model that achieves optimal performance in the presence of an attacker who is able to add a carefully designed adversarial data point to the dataset or perform a rank-one attack on the dataset. By solving the proposed nonsmooth nonconvex-nonconcave minimax problem, the optimal adversary as well as the robust fairness-aware regression model are obtained. For both synthetic data and real-world datasets, numerical results illustrate that the proposed adversarially robust fair models have better performance on poisoned datasets than other fair machine learning models in both prediction accuracy and group-based fairness measure.

We present SpaceQA, to the best of our knowledge the first open-domain QA system in Space mission design. SpaceQA is part of an initiative by the European Space Agency (ESA) to facilitate the access, sharing and reuse of information about Space mission design within the agency and with the public. We adopt a state-of-the-art architecture consisting of a dense retriever and a neural reader and opt for an approach based on transfer learning rather than fine-tuning due to the lack of domain-specific annotated data. Our evaluation on a test set produced by ESA is largely consistent with the results originally reported by the evaluated retrievers and confirms the need of fine tuning for reading comprehension. As of writing this paper, ESA is piloting SpaceQA internally.

Artificial Intelligence (AI) is having a tremendous impact across most areas of science. Applications of AI in healthcare have the potential to improve our ability to detect, diagnose, prognose, and intervene on human disease. For AI models to be used clinically, they need to be made safe, reproducible and robust, and the underlying software framework must be aware of the particularities (e.g. geometry, physiology, physics) of medical data being processed. This work introduces MONAI, a freely available, community-supported, and consortium-led PyTorch-based framework for deep learning in healthcare. MONAI extends PyTorch to support medical data, with a particular focus on imaging, and provide purpose-specific AI model architectures, transformations and utilities that streamline the development and deployment of medical AI models. MONAI follows best practices for software-development, providing an easy-to-use, robust, well-documented, and well-tested software framework. MONAI preserves the simple, additive, and compositional approach of its underlying PyTorch libraries. MONAI is being used by and receiving contributions from research, clinical and industrial teams from around the world, who are pursuing applications spanning nearly every aspect of healthcare.

At the US Patent & Trademark Office in Alexandria, Virginia, artificial intelligence (AI) projects are expediting the patent classification process, helping detect fraud, and expanding examiners' searches for similar patents, enabling them to search through more documents in the same amount of time. And every project started with a pilot project. "Proofs of concept (PoCs) are a key approach we use to learn about new technologies, test business value assumptions, de-risk scale project delivery, and inform full production implementation decisions," says USPTO CIO Jamie Holcombe. Once the pilot proves out, he says, the next step is to determine if it can scale. Indian e-commerce vendor Flipkart has followed a similar process before deploying projects that allow for text and visual search through millions of items for customers who speak 11 different languages.

A spin out of the Human Centered Robotics Lab at the University of Texas at Austin, startup Apptronik has some serious R&D behind it. Two of the company co-founders were part of NASA's Johnson Space Center Valkyrie team, working on the actuators and controls of the humanoid robot, as well as participating in the DARPA Robotics Challenge to build a versatile "hero robot" that could do all the things needed in a disaster relief scenario. These projects became advanced R&D work to eventually commercialize a more versatile robot that fills the need of working in an environment of unstructured tasks. And, despite the look of the robots the company has in its portfolio--like Astra, an upper body humanoid robot designed to operate with and around humans on a mobile platform, and Draco, a biped designed for agile dynamic walking--the company says it's solving a huge problem in manufacturing. "In manufacturing there are structured and highly repeatable tasks. Where we see this going is robots [designed] for the unstructured world," said Jeff Cardenas, Apptronik co-founder and CEO.

A Canadian start-up has developed a voice imitation programme capable of mimicking a person's voice after just a minute of listening to them speak. Developed by AI firm Lyrebird, the algorithm uses machine learning to synthesise speech based on audio samples and is even able to replicate emotion. Lyrebird's algorithm is capable of generating new voices from scratch as well as replicating those of others. After hearing an audio clip, the programme determines the defining feature or "key" to the person's voice and then uses this to generate words from scratch. It even varies the intonations it applies so that a repeated sentence doesn't sound the same way twice.

Iran stands accused by Western powers of supplying drones to Russia for its war against Ukraine, with analysts saying such military cooperation is of immense interest for Tehran at a delicate moment for its theocratic leadership. The United States has denounced as "appalling" Russia's use of Iranian drones after residents of Kyiv and other cites were shaken by a spate of recent attacks. Ukraine has said around 400 Iranian drones have already been used against the civilian population of Ukraine, and Moscow has ordered around 2,000. Tehran has rejected the allegations. Iran and Russia, both former imperial powers who for centuries vied for domination of the Caspian Sea region, have long had a highly nuanced and delicate relationship marked by rivalry and cooperation.

HAI NET General Under Vision, add a dedicated task Legal Protection by Design This project aims to take seriously the fact that the development and deployment of AI systems is not above the law, as decided in constitutional democracies. This feeds into the task of addressing the question of incorporation of fundamental rights protection into the architecture of AI systems including (1) checks and balances of the Rule of Law and (2) requirements imposed by positive law that elaborates fundamental rights protection. A key result of this task will be a report on a coherent set of design principles firmly grounded in relevant positive law, with a clear emphasis on European law (both EU and Council of Europe). To help developers understand the core tenets of the EU legal framework, we have developed two tutorials, one in 2020 on Legal Protection by Design in relation to EU data protection law [hyperlink to Tutorial 2020] and one in 2021 on the European Commission’s proposal of an EU AI Act [hyperlink to Tutorial 2021]. In the Fall of 2022 we will follow up with a Tutorial on the proposed EU AI Liability Directive. Our findings will entail: - A sufficiently detailed overview of legally relevant roles, such as end-users, targeted persons, software developers, hardware manufacturers, those who put AI applications on the market, platforms that integrate service provision both vertical and horizontal, providers of infrastructure (telecom providers, cloud providers, providers of cyber-physical infrastructure, smart grid providers, etc.); - A sufficiently detailed legal vocabulary, explained at the level of AI applications, such as legal subjects, legal objects, legal rights and obligations, private law liability, fundamental rights protection; - High level principles that anchor the Rule of Law: transparency (e.g. explainability, preregistration of research design), accountability (e.g. clear attribution of tort liability, fines by relevant supervisors, criminal law liability), contestability (e.g. the repertoire of legal remedies, adversarial structure of legal procedure).

Originally published on Towards AI the World's Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses. Data and judgment complement AI as core elements of decision-making in war and national security in general. The human-like behavior of AI-based technology raises questions regarding the interfaces between science, technology, and society.

Technology has made significant advancements and has already solved many of the supply chain challenges affecting companies today. However, we can't claim that all the challenges have decreased when compared to previous years. On the contrary, globalisation, trade sanctions, Brexit, an eCommerce revolution and finally a global pandemic are just some of the factors that are complicating an overcomplicated supply chain – especially for companies that might lack the resources of bigger corporations. Developments in AI have assisted in the planning and development of operations across the supply chain. And if the pandemic has taught us one thing, it is the importance of forward planning and anticipating supply chain challenges.