As machine learning (ML) techniques are being increasingly used in many applications, their vulnerability to adversarial attacks becomes well-known. Test time attacks, usually launched by adding adversarial noise to test instances, have been shown effective against the deployed ML models. In practice, one test input may be leveraged by different ML models. Test time attacks targeting a single ML model often neglect their impact on other ML models. In this work, we empirically demonstrate that naively attacking the classifier learning one concept may negatively impact classifiers trained to learn other concepts. For example, for the online image classification scenario, when the Gender classifier is under attack, the (wearing) Glasses classifier is simultaneously attacked with the accuracy dropped from 98.69 to 88.42. This raises an interesting question: is it possible to attack one set of classifiers without impacting the other set that uses the same test instance? Answers to the above research question have interesting implications for protecting privacy against ML model misuse. Attacking ML models that pose unnecessary risks of privacy invasion can be an important tool for protecting individuals from harmful privacy exploitation. In this paper, we address the above research question by developing novel attack techniques that can simultaneously attack one set of ML models while preserving the accuracy of the other. In the case of linear classifiers, we provide a theoretical framework for finding an optimal solution to generate such adversarial examples. Using this theoretical framework, we develop a multi-concept attack strategy in the context of deep learning. Our results demonstrate that our techniques can successfully attack the target classes while protecting the protected classes in many different settings, which is not possible with the existing test-time attack-single strategies.

Machine learning algorithms have become prevalent tools for decision-making in socially sensitive situations, such as determining credit-score ratings or predicting recidivism during parole. It has been recognized that algorithms are capable of learning societal biases, for example with respect to race (Larson, Mattu, Kirchner, and Angwin 2016) or gender (Lambrecht and Tucker 2019; Blau and Kahn 2003), and this realization seeded an important debate in the machine learning community about fairness of algorithms and their impact on decision-making. In order to define and measure discrimination, existing intuitive notions have been statistically formalized, thereby providing fairness metrics. For example, demographic parity (Darlington 1971) requires the protected attribute A (gender/race/religion etc.) to be independent of a constructed classifier or regressor Ŷ, written as Ŷ A. Another notion, termed equality of odds (Hardt, Price, Srebro et al. 2016), requires equal false positive and false negative rates of classifier Ŷ between different groups (females and males for example), written as Ŷ A Y. To this day, various different notions of fairness exist, which are sometimes incompatible (Corbett-Davies and Goel 2018), meaning not of all of them can be achieved for a predictor Ŷ simultaneously. There is still no consensus on which notion of fairness is the correct one. The discussion on algorithmic fairness is, however, not restricted to the machine learning domain. There are many legal and philosophical aspects that have arisen. For example, the legal distinction between disparate impact and disparate treatment (McGinley 2011) is important for assessing fairness from a judicial point of view.

We propose a nonparametric factorization approach for sparsely observed tensors. The sparsity does not mean zero-valued entries are massive or dominated. Rather, it implies the observed entries are very few, and even fewer with the growth of the tensor; this is ubiquitous in practice. Compared with the existent works, our model not only leverages the structural information underlying the observed entry indices, but also provides extra interpretability and flexibility -- it can simultaneously estimate a set of location factors about the intrinsic properties of the tensor nodes, and another set of sociability factors reflecting their extrovert activity in interacting with others; users are free to choose a trade-off between the two types of factors. Specifically, we use hierarchical Gamma processes and Poisson random measures to construct a tensor-valued process, which can freely sample the two types of factors to generate tensors and always guarantees an asymptotic sparsity. We then normalize the tensor process to obtain hierarchical Dirichlet processes to sample each observed entry index, and use a Gaussian process to sample the entry value as a nonlinear function of the factors, so as to capture both the sparse structure properties and complex node relationships. For efficient inference, we use Dirichlet process properties over finite sample partitions, density transformations, and random features to develop a stochastic variational estimation algorithm. We demonstrate the advantage of our method in several benchmark datasets.

We develop methodology for three-dimensional (3D) radial visualization (RadViz) of multidimensional datasets. Our tool, RadViz3D, distributes anchor points uniformly on the 3D unit sphere. We show that this uniform distribution provides the best visualization with minimal artificial visual correlation for data with uncorrelated variables. However, anchor points can be placed exactly equi-distant from each other only for the five Platonic solids, so we provide equi-distant anchor points for these five settings, and approximately equi-distant anchor points via a Fibonacci grid for the other cases. Our methodology, implemented in the R package radviz3d, makes fully 3D RadViz possible and is shown to improve the ability of this nonlinear technique in more faithfully displaying simulated data as well as the crabs, olive oils and wine datasets. Additionally, because radial visualization is naturally suited for compositional data, we use RadViz3D to illustrate (i) the chemical composition of Longquan celadon ceramics and their Jingdezhen imitation over centuries, and (ii) US regional SARS-Cov-2 variants' prevalence in the Covid-19 pandemic during the summer 2021 surge of the Delta variant. Graphical display of multivariate data is important to obtain insight into their properties and similarity or distinctiveness of different groups [1].

Artificial intelligence tools in health care should be safe and effective. They should be fair to people of different races, genders, and geographies. And they should be monitored to ensure they are improving outcomes in the real world. Most participants agreed on those goals in a Food and Drug Administration workshop on the regulation of artificial intelligence late last week. But how to accomplish them remained a source of considerable debate.

In media news today, NBC fact-checks Anthony Fauci's COVID superspreader comments, Jon Stewart says the media is making a'mistake' casting Trump as a'supervillain,' and CNN's Brian Stelter frets that Katie Couric's editing scandal further damages the media's reputation Sen. Bill Cassidy, R-La., told Axios that he favored cognitive tests for aging government leaders in order to make sure their ability to serve the American people remained intact. On Sunday's "Axios on HBO," Cassidy cited past U.S. Senators he said were senile by the end of their times in office to argue a cognitive test applying across all three branches of government would be "a reasonable plan." "The Speaker of the House is 81. Wisdom comes with age, but the science is also clear that we aren't who we were, that we do lose things with age. As a medical professional, is that something we should be thinking about?"

The course will start off at the basics and work all the way through the financial accounting topics generally covered in an undergraduate program. First, we will describe what financial accounting is and the objectives of financial accounting. We will learn how the double-entry accounting system works by applying it to the accounting equation. In other words, we will use an accounting equation to record financial transactions using a double-entry accounting system. We well learn all topics by fist having presentations and then applying the skills using Excel practice problems.

Los Alamos National Laboratory, a multidisciplinary research institution engaged in strategic science on behalf of national security, is managed by Triad, a public service oriented, national security science organization equally owned by its three founding members: Battelle Memorial Institute (Battelle), the Texas A&M University System (TAMUS), and the Regents of the University of California (UC) for the Department of Energy's National Nuclear Security Administration. Los Alamos enhances national security by ensuring the safety and reliability of the U.S. nuclear stockpile, developing technologies to reduce threats from weapons of mass destruction, and solving problems related to energy, environment, infrastructure, health, and global security concerns.

This week's publication of the Pandora Papers–which the International Consortium of International Journalists based on a trove of private data leaked from offshore tax havens–showcased the alarming extent of fraud and corruption in the world. While big data tech like graph analytics and machine learning can help to a shine light on bad actors, we'll always be playing catch up, fraud hunters tell Datanami. The sheer numbers behind the Pandora Papers, which the ICIJ published on October 3, 2021, are staggering. The ICIJ was provided with 11.9 million documents, including text files, PDFs, images, emails, and spreadsheets, from 14 offshore tax havens, totaling 2.9 TB of data. The documents contained information about 27,000 shell companies created to protect the assets of 29,000 beneficial owners, including 130 billionaires and 330 politicians from 90 countries.

At the outbreak of World War I, the French army was mobilised in the fashion of Napoleonic times. On horseback and equipped with swords, the cuirassiers wore bright tricolour uniforms topped with feathers--the same get-up as when they swept through Europe a hundred years earlier. Vast fields were filled with trenches, barbed wire, poison gas and machine gun fire--plunging the ill-equipped soldiers into a violent hellscape of industrial-scale slaughter. Only three decades after the first World War I bayonet charge across no man's land, the US was able to incinerate entire cities with a single (nuclear) bomb blast. And since the destruction of Hiroshima and Nagasaki in 1945, our rulers' methods of war have been made yet more deadly and "efficient".