This paper advances the understanding of how the size of a machine learning model affects its vulnerability to poisoning, despite state-of-the-art defenses. Given isotropic random honest feature vectors and the geometric median (or clipped mean) as the robust gradient aggregator rule, we essentially prove that, perhaps surprisingly, linear and logistic regressions with $D \geq 169 H^2/P^2$ parameters are subject to arbitrary model manipulation by poisoners, where $H$ and $P$ are the numbers of honestly labeled and poisoned data points used for training. Our experiments go on exposing a fundamental tradeoff between augmenting model expressivity and increasing the poisoners' attack surface, on both synthetic data, and on MNIST & FashionMNIST data for linear classifiers with random features. We also discuss potential implications for source-based learning and neural nets.

Whether deterministic or stochastic, models can be viewed as functions designed to approximate a specific quantity of interest. We propose a data-driven framework that aggregates predictions from diverse models into a single, more accurate output. This aggregation approach exploits each model's strengths to enhance overall accuracy. It is non-intrusive - treating models as black-box functions - model-agnostic, requires minimal assumptions, and can combine outputs from a wide range of models, including those from machine learning and numerical solvers. We argue that the aggregation process should be point-wise linear and propose two methods to find an optimal aggregate: Minimal Error Aggregation (MEA), which minimizes the aggregate's prediction error, and Minimal Variance Aggregation (MVA), which minimizes its variance. While MEA is inherently more accurate when correlations between models and the target quantity are perfectly known, Minimal Empirical Variance Aggregation (MEVA), an empirical version of MVA - consistently outperforms Minimal Empirical Error Aggregation (MEEA), the empirical counterpart of MEA, when these correlations must be estimated from data. The key difference is that MEVA constructs an aggregate by estimating model errors, while MEEA treats the models as features for direct interpolation of the quantity of interest. This makes MEEA more susceptible to overfitting and poor generalization, where the aggregate may underperform individual models during testing. We demonstrate the versatility and effectiveness of our framework in various applications, such as data science and partial differential equations, showing how it successfully integrates traditional solvers with machine learning models to improve both robustness and accuracy.

In an address to the 79th United Nations General Assembly Tuesday, Iranian President Masoud Pezeshkian claimed to be the one playing peacemaker in the Middle East and, in a juxtaposition, accused Israel of supporting terrorism. Pezeshkian called on the U.N. to "examine" modern history and said, "Iran has never initiated a war. It has only defended itself heroically against external aggression, causing the aggressors to regret their actions," Pezeshkian said, adding that Iran does not "occupy" territory or exploit resources for other countries. "It has repeatedly offered various proposals to its neighbors and international fora aimed at establishing lasting peace and stability," he said. "We have emphasized the importance of unity in the region and establishing a strong region." Iran's President Masoud Pezeshkian walks, on the sidelines of the 79th United Nations General Assembly at U.N. headquarters in New York, U.S., September 24, 2024.

For years now, AI has undermined the public's ability to trust what it sees, hears, and reads. The Republican National Committee released a provocative ad offering an "AI-generated look into the country's possible future if Joe Biden is re-elected," showing apocalyptic, machine-made images of ruined cityscapes and chaos at the border. Fake robocalls purporting to be from Biden urged New Hampshire residents not to vote in the 2024 primary election. This summer, the Department of Justice cracked down on a Russian bot farm that was using AI to impersonate Americans on social media, and OpenAI disrupted an Iranian group using ChatGPT to generate fake social-media comments. It's not altogether clear what damage AI itself may cause, though the reasons for concern are obvious--the technology makes it easier for bad actors to construct highly persuasive and misleading content.

Fox News' Bill Hemmer discusses his trip to join the U.S. Navy in the Arctic Circle and tour a nuclear submarine. When the Biden administration nominated Michael Sfraga to be special ambassador to the Arctic, he failed to disclose his deep history with Russia and China. The Senate is expected to vote on Sfraga's confirmation on Tuesday – over a year after his nomination, which was held up by Republicans who claim he is too close to U.S. adversaries. Sfraga has traveled extensively across Russia and China, and even spoke at an event where Russian President Vladimir Putin gave the headline address. An Alaskan and geographer by background, Sfraga chairs the Polar Institute and the U.S. Arctic Research Commission.

He used to go to the Regal City North cinema in Chicago three times a week. But he never goes there anymore--because of the parking lot. The parking garage, which is directly connected to the theater, once charged 2 for parking. Then it fell into disrepair sometime during the pandemic. "Someone destroyed the crossbar at the exit, and the stairwells had broken glass in them. They never replaced the glass for the stairwell," Spencer told me.

When the generative AI boom kicked off, one of the biggest concerns was that hyperrealistic deepfakes could be used to influence elections. But new research from the Alan Turing Institute recently found that AI-generated falsehoods seem to have had no effect on election results around the world so far this year. However, one of the most consequential elections of the year is still ahead of us. In just over a month, Americans will head to the polls to choose Donald Trump or Kamala Harris as their next president. And, so far, external state actors are relying far more heavily on old tried-and-tested tactics than newfangled AI tools to interfere.

The former chairman of the House Select Committee on the Chinese Communist Party warned about a fast-moving software and technology race between the United States and China, arguing the weaponization of supply chains could force a showdown between the free world and its totalitarian rivals. Former Rep. Mike Gallagher, R-Wis., told Fox News chief political anchor Bret Baier about a Wall Street Journal (WSJ) op-ed he wrote Sunday, outlining his concerns about China's growing technological dominance. "On the modern battlefield, we need to not only know our adversary but know ourselves and map our supply chain in great detail," he said Monday on "Special Report." Gallagher, the head of defense for Palantir Technologies, a Denver-based software company, highlighted how China could use its manufactured port cranes across the world to disrupt international commerce if the United States were to get into a conflict with China over Taiwan. "The Biden administration recently warned that Chinese-made port cranes could be'controlled... from remote locations.' European companies found that Chinese groups may have gained access to the systems that control cargo ships. Billions of endpoints connect to the internet, including sensors and devices that physically interact with critical infrastructure. Anyone with control over a portion of the technology stack such as semiconductors, cellular modules, or hardware devices, can use it to snoop, incapacitate or kill," he wrote in the WSJ.

A few months ago, I flew to Houston to visit a small startup called Lunar Resources, which aspires to build the largest telescope in the solar system--not on Earth but on the far side of the moon. Houston is nicknamed Space City; on the ride from the airport, I passed the ballpark where the Astros play, and, outside a McDonald's on East NASA Parkway, I saw a giant sculpture of an astronaut holding French fries. I found Lunar Resources in a boxy building where the company leases square footage from the aerospace contractor Lockheed Martin. Elliot Carol, the C.E.O. and co-founder of Lunar Resources, is thirty-three, with a cherubic face and curly hair speckled with gray. Although he grew up in Connecticut and previously worked as a hedge-fund manager, he was wearing black cowboy boots.

When the generative-AI boom first kicked off, one of the biggest concerns among pundits and experts was that hyperrealistic AI deepfakes could be used to influence elections. But new research from the Alan Turing Institute in the UK shows that those fears might have been overblown. AI-generated falsehoods and deepfakes seem to have had no effect on election results in the UK, France, and the European Parliament, as well as other elections around the world so far this year. Instead of using generative AI to interfere in elections, state actors such as Russia are relying on well-established techniques--such as social bots that flood comment sections--to sow division and create confusion, says Sam Stockwell, the researcher who conducted the study. But one of the most consequential elections of the year is still ahead of us.