Nearly two thousand government bodies, including police departments and public schools, have been using Clearview AI without oversight. Buzzfeed News reports that employees from 1,803 public bodies used the controversial facial-recognition platform without authorization from bosses. Reporters contacted a number of agency heads, many of which said they were unaware their employees were accessing the system. A database of searches, outlining which agencies were able to access the platform, and how many queries were made, was leaked to Buzzfeed by an anonymous source. It has published a version of the database online, enabling you to examine how many times each department has used the tool.

The university researchers built an agile contraption about the size of an average climbing lizard. The machine is nine inches long, weighs under a half-pound, and has legs and feet designed to mimic the way climbing lizards move. It is built primarily from 3-D-printed parts, with joints at the spine so it can slither and joints at the shoulders so its feet can move backward and forward. The feet have pushpins for claws, allowing them to grip into surfaces and release with ease.

In this work, we consider a binary classification problem and cast it into a binary hypothesis testing framework, where the observations can be perturbed by an adversary. To improve the adversarial robustness of a classifier, we include an abstaining option, where the classifier abstains from taking a decision when it has low confidence about the prediction. We propose metrics to quantify the nominal performance of a classifier with abstaining option and its robustness against adversarial perturbations. We show that there exist a tradeoff between the two metrics regardless of what method is used to choose the abstaining region. Our results imply that the robustness of a classifier with abstaining can only be improved at the expense of its nominal performance. Further, we provide necessary conditions to design the abstaining region for a 1-dimensional binary classification problem. We validate our theoretical results on the MNIST dataset, where we numerically show that the tradeoff between performance and robustness also exist for the general multi-class classification problems.

Confidence in the regulatory environment is crucial to enable responsible AI innovation and foster the social acceptance of these powerful new technologies. One notable source of uncertainty is, however, that the existing legal liability system is unable to assign responsibility where a potentially harmful conduct and/or the harm itself are unforeseeable, yet some instantiations of AI and/or the harms they may trigger are not foreseeable in the legal sense. The unpredictability of how courts would handle such cases makes the risks involved in the investment and use of AI difficult to calculate with confidence, creating an environment that is not conducive to innovation and may deprive society of some benefits AI could provide. To tackle this problem, we propose to draw insights from financial regulatory best practices and establish a system of AI guarantee schemes. We envisage the system to form part of the broader market-structuring regulatory frameworks, with the primary function to provide a readily available, clear, and transparent funding mechanism to compensate claims that are either extremely hard or impossible to realize via conventional litigation. We propose it to be at least partially industry-funded. Funding arrangements should depend on whether it would pursue other potential policy goals aimed more broadly at controlling the trajectory of AI innovation to increase economic and social welfare worldwide. Because of the global relevance of the issue, rather than focusing on any particular legal system, we trace relevant developments across multiple jurisdictions and engage in a high-level, comparative conceptual debate around the suitability of the foreseeability concept to limit legal liability. The paper also refrains from confronting the intricacies of the case law of specific jurisdictions for now and—recognizing the importance of this task—leaves this to further research in support of the legal system’s incremental adaptation to the novel challenges of present and future AI technologies. This article appears in the special track on AI and Society.

Manual labelling of training examples is common practice in supervised learning. When the labelling task is of non-trivial difficulty, the supplied labels may not be equal to the ground-truth labels, and label noise is introduced into the training dataset. If the manual annotation is carried out by multiple experts, the same training example can be given different class assignments by different experts, which is indicative of label noise. In the framework of model-based classification, a simple, but key observation is that when the manual labels are sampled using the posterior probabilities of class membership, the noisy labels are as valuable as the ground-truth labels in terms of statistical information. A relaxation of this process is a random effects model for imperfect labelling by a group that uses approximate posterior probabilities of class membership. The relative efficiency of logistic regression using the noisy labels compared to logistic regression using the ground-truth labels can then be derived. The main finding is that logistic regression can be robust to label noise when label noise and classification difficulty are positively correlated. In particular, when classification difficulty is the only source of label errors, multiple sets of noisy labels can supply more information for the estimation of a classification rule compared to the single set of ground-truth labels.

Mixture of experts (MoE) is a popular class of models in statistics and machine learning that has sustained attention over the years, due to its flexibility and effectiveness. We consider the Gaussian-gated localized MoE (GLoME) regression model for modeling heterogeneous data. This model poses challenging questions with respect to the statistical estimation and model selection problems, including feature selection, both from the computational and theoretical points of view. We study the problem of estimating the number of components of the GLoME model, in a penalized maximum likelihood estimation framework. We provide a lower bound on the penalty that ensures a weak oracle inequality is satisfied by our estimator. To support our theoretical result, we perform numerical experiments on simulated and real data, which illustrate the performance of our finite-sample oracle inequality.

Shapley values have become one of the most popular feature attribution explanation methods. However, most prior work has focused on post-hoc Shapley explanations, which can be computationally demanding due to its exponential time complexity and preclude model regularization based on Shapley explanations during training. Thus, we propose to incorporate Shapley values themselves as latent representations in deep models thereby making Shapley explanations first-class citizens in the modeling paradigm. This intrinsic explanation approach enables layer-wise explanations, explanation regularization of the model during training, and fast explanation computation at test time. We define the Shapley transform that transforms the input into a Shapley representation given a specific function. We operationalize the Shapley transform as a neural network module and construct both shallow and deep networks, called ShapNets, by composing Shapley modules. We prove that our Shallow ShapNets compute the exact Shapley values and our Deep ShapNets maintain the missingness and accuracy properties of Shapley values. We demonstrate on synthetic and real-world datasets that our ShapNets enable layer-wise Shapley explanations, novel Shapley regularizations during training, and fast computation while maintaining reasonable performance. Code is available at https://github.com/inouye-lab/ShapleyExplanationNetworks.

James Cameron's obsession with the ocean deep began when he was an adolescent, in rural Canada. He read National Geographic accounts of deep-sea excursions and idolized Jacques Cousteau and his crew. "They always had this great French sense of style," he said recently. "They breathed it, quite literally, with their Aqua-Lungs. They got in their silver wetsuits and went exploring. It was like a science-fiction movie. I said, 'I need to do that.' " The problem: he lived five hundred kilometres from the nearest ocean.

Australians are being urged to secure their social media accounts after the details of more than 500 million global Facebook users were found online in a massive data breach. The details published freely online included names, phone numbers, email addresses, account IDs and bios. In a statement, Facebook said the leaked information was old, and came from a problem it had resolved in 2019, but experts told Guardian Australia the data could still cause problems for users caught up in the breach. So what might hackers do with your info? How can you check if your data was leaked?

The global ambitions of a carbon-neutral society necessitate a stable and robust smart grid that capitalises on frequency reserves of renewable energy. Frequency reserves are resources that adjust power production or consumption in real time to react to a power grid frequency deviation. Revenue generation motivates the availability of these resources for managing such deviations. However, limited research has been conducted on data-driven decisions and optimal bidding strategies for trading such capacities in multiple frequency reserves markets. We address this limitation by making the following research contributions. Firstly, a generalised model is designed based on an extensive study of critical characteristics of global frequency reserves markets. Secondly, three bidding strategies are proposed, based on this market model, to capitalise on price peaks in multi-stage markets. Two strategies are proposed for non-reschedulable loads, in which case the bidding strategy aims to select the market with the highest anticipated price, and the third bidding strategy focuses on rescheduling loads to hours on which highest reserve market prices are anticipated. The third research contribution is an Artificial Intelligence (AI) based bidding optimization framework that implements these three strategies, with novel uncertainty metrics that supplement data-driven price prediction. Finally, the framework is evaluated empirically using a case study of multiple frequency reserves markets in Finland. The results from this evaluation confirm the effectiveness of the proposed bidding strategies and the AI-based bidding optimization framework in terms of cumulative revenue generation, leading to an increased availability of frequency reserves.