We study mean estimation for a Gaussian distribution with identity covariance in $\mathbb{R}^d$ under a missing data scheme termed realizable $ε$-contamination model. In this model an adversary can choose a function $r(x)$ between 0 and $ε$ and each sample $x$ goes missing with probability $r(x)$. Recent work Ma et al., 2024 proposed this model as an intermediate-strength setting between Missing Completely At Random (MCAR) -- where missingness is independent of the data -- and Missing Not At Random (MNAR) -- where missingness may depend arbitrarily on the sample values and can lead to non-identifiability issues. That work established information-theoretic upper and lower bounds for mean estimation in the realizable contamination model. Their proposed estimators incur runtime exponential in the dimension, leaving open the possibility of computationally efficient algorithms in high dimensions. In this work, we establish an information-computation gap in the Statistical Query model (and, as a corollary, for Low-Degree Polynomials and PTF tests), showing that algorithms must either use substantially more samples than information-theoretically necessary or incur exponential runtime. We complement our SQ lower bound with an algorithm whose sample-time tradeoff nearly matches our lower bound. Together, these results qualitatively characterize the complexity of Gaussian mean estimation under $ε$-realizable contamination.

Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems.

Elon Musk is making a big bet on his future vision - will it work? Reports suggest that Elon Musk is eyeing up a merger involving SpaceX, Tesla and xAI, but what does he hope to achieve by consolidating his business empire? Elon Musk is a busy man, heading up multiple billion-dollar companies. While he is increasingly a divisive figure, there is no doubt that Tesla and SpaceX, his two most important ventures, have done much to advance the future of electric cars and spacecraft, respectively. But a series of corporate moves this week suggests Musk has a new vision of the future - and he may be combining all his companies to get there.

AI company's chatbot faces criticism over its generation of sexualized, nonconsensual images of women and girls Elon Musk's artificial intelligence company has raised $20bn in its latest funding round, the startup announced Tuesday, even as its marquee chatbot Grok faces backlash over generating sexualized, nonconsensual images of women and underage girls. The funding round exceeded its initial $15bn target, according to xAI's press release. The company touted Grok's image-generation abilities in the announcement of its latest funding round. Nonetheless, the company has been able to win government contracts and billions of dollars in investment amid the AI boom. Over the past week, Grok has responded to tens of thousands of prompts from users on X requesting the chatbot remove women's clothing in images or pose them in sexualized ways.

Though the drama surrounding Elon Musk was frequently absurd and unpredictable, it was also consequential. Though the drama surrounding Elon Musk was frequently absurd and unpredictable, it was also consequential. Elon Musk's 2025 recap: how the world's richest person became its most chaotic How the tech CEO and'Dogefather' made a mess of the year - from an apparent Nazi salute during his White House tenure to Tesla sales slumps and Starship explosions T he year of 2025 was dizzying for Elon Musk . The tech titan began the year holding court with Donald Trump in Washington DC. As the months ticked by, one public appearance after another baffled the US and the world.

Generative models are increasingly used to produce privacy-preserving synthetic data as a safe alternative to sharing sensitive training datasets. However, we demonstrate that such synthetic releases can still leak information about the underlying training samples through structural overlap in the data manifold. We propose a black-box membership inference attack that exploits this vulnerability without requiring access to model internals or real data. The attacker repeatedly queries the generative model to obtain large numbers of synthetic samples, performs unsupervised clustering to identify dense regions of the synthetic distribution, and then analyzes cluster medoids and neighborhoods that correspond to high-density regions in the original training data. These neighborhoods act as proxies for training samples, enabling the adversary to infer membership or reconstruct approximate records. Our experiments across healthcare, finance, and other sensitive domains show that cluster overlap between real and synthetic data leads to measurable membership leakage-even when the generator is trained with differential privacy or other noise mechanisms. The results highlight an under-explored attack surface in synthetic data generation pipelines and call for stronger privacy guarantees that account for distributional neighborhood inference rather than sample-level memorization alone, underscoring its role in privacy-preserving data publishing. Implementation and evaluation code are publicly available at:github.com/Cluster-Medoid-Leakage-Attack.

Scaling the distribution of automated vehicles requires handling various unexpected and possibly dangerous situations, termed corner cases (CC). Since many modules of automated driving systems are based on machine learning (ML), CC are an essential part of the data for their development. However, there is only a limited amount of CC data in large-scale data collections, which makes them challenging in the context of ML. With a better understanding of CC, offline applications, e.g., dataset analysis, and online methods, e.g., improved performance of automated driving systems, can be improved. While there are knowledge-based descriptions and taxonomies for CC, there is little research on machine-interpretable descriptions. In this extended abstract, we will give a brief overview of the challenges and goals of such a description.

Connected and autonomous vehicles across land, water, and air must often operate in dynamic, unpredictable environments with limited communication, no centralized control, and partial observability. These real-world constraints pose significant challenges for coordination, particularly when vehicles pursue individual objectives. To address this, we propose a decentralized Multi-Agent Reinforcement Learning (MARL) framework that enables vehicles, acting as agents, to communicate selectively based on local goals and observations. This goal-aware communication strategy allows agents to share only relevant information, enhancing collaboration while respecting visibility limitations. We validate our approach in complex multi-agent navigation tasks featuring obstacles and dynamic agent populations. Results show that our method significantly improves task success rates and reduces time-to-goal compared to non-cooperative baselines. Moreover, task performance remains stable as the number of agents increases, demonstrating scalability. These findings highlight the potential of decentralized, goal-driven MARL to support effective coordination in realistic multi-vehicle systems operating across diverse domains.