This anti-detection starter pack came recommended for those looking to shield themselves from government surveillance while protesting in support of Black Lives Matter. In the future, the Federal Aviation Agency might be a resource added to the list. The gamut of surveillance tools used during protests runs wide. It's unlikely that your Twitter account was hacked, much like Donald Trump's was thought to be last month, to determine your location while protesting. But it may have been analyzed with a social media scanning tool.

Much of the previous machine learning (ML) fairness literature assumes that protected features such as race and sex are present in the dataset, and relies upon them to mitigate fairness concerns. However, in practice factors like privacy and regulation often preclude the collection of protected features, or their use for training or inference, severely limiting the applicability of traditional fairness research. Therefore we ask: How can we train an ML model to improve fairness when we do not even know the protected group memberships? In this work we address this problem by proposing Adversarially Reweighted Learning (ARL). In particular, we hypothesize that non-protected features and task labels are valuable for identifying fairness issues, and can be used to co-train an adversarial reweighting approach for improving fairness. Our results show that {ARL} improves Rawlsian Max-Min fairness, with notable AUC improvements for worst-case protected groups in multiple datasets, outperforming state-of-the-art alternatives.

With the current ongoing debate about fairness, explainability and transparency of machine learning models, their application in high-impact clinical decision-making systems must be scrutinized. We consider a real-life example of risk estimation before surgery and investigate the potential for bias or unfairness of a variety of algorithms. Our approach creates transparent documentation of potential bias so that the users can apply the model carefully. We augment a model-card like analysis using propensity scores with a decision-tree based guide for clinicians that would identify predictable shortcomings of the model. In addition to functioning as a guide for users, we propose that it can guide the algorithm development and informatics team to focus on data sources and structures that can address these shortcomings.

Across machine learning (ML) sub-disciplines researchers make mathematical assumptions to facilitate proof-writing. While such assumptions are necessary for providing mathematical guarantees for how algorithms behave, they also necessarily limit the applicability of these algorithms to different problem settings. This practice is known--in fact, obvious-- and accepted in ML research. However, similar attention is not paid to the normative assumptions that ground this work. I argue such assumptions are equally as important, especially in areas of ML with clear social impact, such as fairness. This is because, similar to how mathematical assumptions constrain applicability, normative assumptions also limit algorithm applicability to certain problem domains. I show that, in existing papers published in top venues, once normative assumptions are clarified, it is often possible to get unclear or contradictory results. While the mathematical assumptions and results are sound, the implicit normative assumptions and accompanying normative results contraindicate using these methods in practical fairness applications.

NLP research has attained high performances in abusive language detection as a supervised classification task. While in research settings, training and test datasets are usually obtained from similar data samples, in practice systems are often applied on data that are different from the training set in topic and class distributions. Also, the ambiguity in class definitions inherited in this task aggravates the discrepancies between source and target datasets. We explore the topic bias and the task formulation bias in cross-dataset generalization. We show that the benign examples in the Wikipedia Detox dataset are biased towards platform-specific topics. We identify these examples using unsupervised topic modeling and manual inspection of topics' keywords. Removing these topics increases cross-dataset generalization, without reducing in-domain classification performance. For a robust dataset design, we suggest applying inexpensive unsupervised methods to inspect the collected data and downsize the non-generalizable content before manually annotating for class labels.

A team of researchers has identified a set of cultural stereotypes that are introduced into artificial intelligence models for language early in their development--a finding that adds to our understanding of the factors that influence results yielded by search engines and other AI-driven tools. "Our work identifies stereotypes about people that widely used AI language models pick up as they learn English. The models we're looking at, and others like them for other languages, are the building blocks of most modern language technologies, from translation systems to question-answering personal assistants to industry tools for resume screening, highlighting the real danger posed by the use of these technologies in their current state," says Sam Bowman, an assistant professor at NYU's Department of Linguistics and Center for Data Science and the paper's senior author. "We expect this effort and related projects will encourage future research towards building more fair language processing systems." The work dovetails with recent scholarship, such as Safiya Umoja Noble's "Algorithms of Oppression: How Search Engines Reinforce Racism" (NYU Press, 2018), which chronicles how racial and other biases have plagued widely used language technologies.

In the aftermath of the Lafayette Square protests in June, police in Washington DC used facial recognition technology to identify a protestor who had allegedly punched an officer in the face. They found the man after feeding an image of him they found on Twitter through a previously undisclosed database called the National Capital Region Facial Recognition Investigative Leads System (NCRFRILS). This is the first time we're learning of this database, despite the fact it's been used in other cases related to human trafficking and bank robberies. According to The Washington Post, 14 local and federal agencies have used the system more than 12,000 times since 2019. It's part of a pilot program the Metropolitan Washington Council of Goverments has been operating since 2017.

Most importantly, all constructive feedback should be well received. You can accomplish this by letting your commenter feel your enthusiasm and accepting attitude, so that they're comfortable voicing their honest opinions. That way you get the most direct feedback. Tip #2 - Be mindful of data ethics. Early on in your career, you're just trying to get the hang of things.

Can broader datasets help developers avoid accidentally perpetuating deep-rooted biases in vital institutions like healthcare and education? AI in healthcare has a bias problem. Last year, it came to light that six algorithms used on an estimated 60-100 million patients nationwide were prioritizing care coordination for white patients over black patients for the same level of illness. The algorithm was trained on costs in insurance claims data, predicting which patients would be expensive in the future based on who was expensive in the past. Historically, less is spent on black patients than white patients, so the algorithm ended up perpetuating existing bias in healthcare.

Artificial Intelligence, for most people, is a tech that powers chatbots or image recognition at best – basically, a software that tells images of cats from dogs. Others view it as a serious threat to their regular day jobs. Regardless of its impact on their lives, people view AI as a technology with tremendous future potential. While the future of AI elicits awe and fear, its impact on the present remains largely unacknowledged. From shortlisting resumes to spreading propaganda, AI is working harder on us than most of us know.