Modern news aggregators do the hard work of organizing a large news stream, creating collections for a given news story with tens of source options. This paper shows that navigating large source collections for a news story can be challenging without further guidance. In this work, we design three interfaces -- the Annotated Article, the Recomposed Article, and the Question Grid -- aimed at accompanying news readers in discovering coverage diversity while they read. A first usability study with 10 journalism experts confirms the designed interfaces all reveal coverage diversity and determine each interface's potential use cases and audiences. In a second usability study, we developed and implemented a reading exercise with 95 novice news readers to measure exposure to coverage diversity. Results show that Annotated Article users are able to answer questions 34% more completely than with two existing interfaces while finding the interface equally easy to use.

A multitude of work has shown that machine learning-based medical diagnosis systems can be biased against certain subgroups of people. This has motivated a growing number of bias mitigation algorithms that aim to address fairness issues in machine learning. However, it is difficult to compare their effectiveness in medical imaging for two reasons. First, there is little consensus on the criteria to assess fairness. Second, existing bias mitigation algorithms are developed under different settings, e.g., datasets, model selection strategies, backbones, and fairness metrics, making a direct comparison and evaluation based on existing results impossible. In this work, we introduce MEDFAIR, a framework to benchmark the fairness of machine learning models for medical imaging. MEDFAIR covers eleven algorithms from various categories, nine datasets from different imaging modalities, and three model selection criteria. Through extensive experiments, we find that the under-studied issue of model selection criterion can have a significant impact on fairness outcomes; while in contrast, state-of-the-art bias mitigation algorithms do not significantly improve fairness outcomes over empirical risk minimization (ERM) in both in-distribution and out-of-distribution settings. We evaluate fairness from various perspectives and make recommendations for different medical application scenarios that require different ethical principles. Our framework provides a reproducible and easy-to-use entry point for the development and evaluation of future bias mitigation algorithms in deep learning. Code is available at https://github.com/ys-zong/MEDFAIR.

How can we collect the most useful labels to learn a model selection policy, when presented with arbitrary heterogeneous data streams? In this paper, we formulate this task as an online contextual active model selection problem, where at each round the learner receives an unlabeled data point along with a context. The goal is to output the best model for any given context without obtaining an excessive amount of labels. In particular, we focus on the task of selecting pre-trained classifiers, and propose a contextual active model selection algorithm (CAMS), which relies on a novel uncertainty sampling query criterion defined on a given policy class for adaptive model selection. In comparison to prior art, our algorithm does not assume a globally optimal model. We provide rigorous theoretical analysis for the regret and query complexity under both adversarial and stochastic settings. Our experiments on several benchmark classification datasets demonstrate the algorithm's effectiveness in terms of both regret and query complexity. Notably, to achieve the same accuracy, CAMS incurs less than 10% of the label cost when compared to the best online model selection baselines on CIFAR10.

Scientists have taken a key step toward harnessing a form of artificial intelligence known as deep reinforcement learning, or DRL, to protect computer networks. When faced with sophisticated cyberattacks in a rigorous simulation setting, deep reinforcement learning was effective at stopping adversaries from reaching their goals up to 95 percent of the time. The outcome offers promise for a role for autonomous AI in proactive cyber defense. Scientists from the Department of Energy's Pacific Northwest National Laboratory documented their findings in a research paper and presented their work Feb. 14 at a workshop on AI for Cybersecurity during the annual meeting of the Association for the Advancement of Artificial Intelligence in Washington, D.C. The starting point was the development of a simulation environment to test multistage attack scenarios involving distinct types of adversaries.

After years selling its controversial Full-Self Driving software upgrade for thousands of dollars, Tesla today issued a recall for every one of the nearly 363,000 vehicles using the feature. The move was prompted by a US government agency saying the software had in "rare circumstances" put drivers in danger and could increase the risk of a crash in everyday situations. Recalls are common in the auto industry and mostly target particular parts or road situations. Tesla's latest recall is sweeping, with the National Highway Traffic Safety Administration saying the Full Self-Driving software can break local traffic laws and act in a way the driver doesn't expect in a grab bag of road situations. According to the agency's filing, those include driving through a yellow light on the verge of turning red; not properly stopping at a stop sign; speeding, due to failing to detect a road sign or because the driver has set their car to default to a faster speed; and making unexpected lane changes to move out of turn-only lanes when going straight through an intersection.

As the fervor around generative AI grows, critics have called on the creators of the tech to take steps to mitigate its potentially harmful effects. In particular, text-generating AI in particular has gotten a lot of attention -- and with good reason. Students could use it to plagiarize, content farms could use it to spam and bad actors could use it to spread misinformation. OpenAI bowed to pressure several weeks ago, releasing a classifier tool that attempts to distinguish between human-written and synthetic text. But it's not particularly accurate; OpenAI estimates that it misses 74% of AI-generated text. In the absence of a reliable way to spot text originating from an AI, a cottage industry of detector services has sprung up.

Tesla just realized that testing "self-driving" vehicle technology on public roads isn't such a good idea, after all. Today, the automaker recalled nearly 363,000 cars equipped with its "Full Self-Driving" technology after a report by the National Highway Traffic Safety Administration found that the Autosteer feature "led to an unreasonable risk to motor vehicle safety based on insufficient adherence to traffic safety laws," the Associated Press reports. The FSD Beta system may allow the vehicle to act unsafe around intersections, such as traveling straight through an intersection while in a turn-only lane, entering a stop sign-controlled intersection without coming to a complete stop, or proceeding into an intersection during a steady yellow traffic signal without due caution. In addition, the system may respond insufficiently to changes in posted speed limits or not adequately account for the driver's adjustment of the vehicle's speed to exceed posted speed limits. As I've written previously, FSD has been linked to multiple deaths.

Los Angeles, California – The United States military shot down a flurry of objects this month: a large object it identified as a Chinese surveillance balloon followed by three smaller objects that the government said might be "benign". The airborne objects were drifting through airspace increasingly crowded with commercial and amateur balloons, drones and possible aerial surveillance craft belonging to adversaries. Their rising numbers pose a challenge to aviators and government agencies. Experts say that while heavy commercial balloons must meet strict Federal Aviation Administration (FAA) regulations, lighter amateur balloons are exempt from most rules, and the FAA might not be able to track them. Military and intelligence officials found no evidence that the three smaller objects were conducting surveillance for another country, and they were not sending communication signals, National Security Council spokesman John Kirby said at a White House briefing on Monday.

Fox News contributor Gen. Keith Kellogg on Iran's president claiming former President Trump must be prosecuted for his involvement in the killing of Iranian Quds Force Commander Qassem Soleimani. A woman accused of luring a man to a Las Vegas area hotel and stabbing him in a revenge plot over the U.S. takedown of an Iranian general has been kicked off of a Texas campus where she had enrolled under the radar despite a Nevada judge ordering her house arrest. Officials at the University of Texas at Dallas told Fox News Digital Thursday that Nika Nikoubin was admitted to the school for the spring 2023 semester. "University officials recently became aware that she was charged with a crime and is under the jurisdiction of a Nevada court," the school said. "Because the safety of our campus and our community is of utmost importance, we have removed her from campus. The UT Dallas Police will monitor the student's compliance with the removal order."

Fox News correspondent Mark Meredith has the latest on ChatGPT on'Special Report.' ChatGPT has become a global phenomenon and is widely seen as a milestone in artificial intelligence, but as more and more users explore its capability, many are pointing out that, like humans, it has an ideology and bias of its own. OpenAI, an American artificial intelligence research company, is behind ChatGPT, a free chatbot launched late last year that has gone viral for its capability in writing essays and reports for slacking students, its sophistication in discussing a wide variety of subjects as well as its skills in storytelling. However, several users, many of them conservative, are sounding the alarm that ChatGPT is not as objective and nonpartisan as one would expect from a machine. Twitter user Echo Chamber asked ChatGPT to "create a poem admiring Donald Trump," a request the bot rejected, replying it was not able to since "it is not in my capacity to have opinions or feelings about any specific person."