Secure aggregation promises a heightened level of privacy in federated learning, maintaining that a server only has access to a decrypted aggregate update. Within this setting, linear layer leakage methods are the only data reconstruction attacks able to scale and achieve a high leakage rate regardless of the number of clients or batch size. This is done through increasing the size of an injected fully-connected (FC) layer. However, this results in a resource overhead which grows larger with an increasing number of clients. We show that this resource overhead is caused by an incorrect perspective in all prior work that treats an attack on an aggregate update in the same way as an individual update with a larger batch size. Instead, by attacking the update from the perspective that aggregation is combining multiple individual updates, this allows the application of sparsity to alleviate resource overhead. We show that the use of sparsity can decrease the model size overhead by over 327$\times$ and the computation time by 3.34$\times$ compared to SOTA while maintaining equivalent total leakage rate, 77% even with $1000$ clients in aggregation.

Moir\'e engineering in atomically thin van der Waals heterostructures creates artificial quantum materials with designer properties. We solve the many-body problem of interacting electrons confined to a moir\'e superlattice potential minimum (the moir\'e atom) using a 2D fermionic neural network. We show that strong Coulomb interactions in combination with the anisotropic moir\'e potential lead to striking ``Wigner molecule" charge density distributions observable with scanning tunneling microscopy.

A quantum neural network (QNN) is a parameterized mapping efficiently implementable on near-term Noisy Intermediate-Scale Quantum (NISQ) computers. It can be used for supervised learning when combined with classical gradient-based optimizers. Despite the existing empirical and theoretical investigations, the convergence of QNN training is not fully understood. Inspired by the success of the neural tangent kernels (NTKs) in probing into the dynamics of classical neural networks, a recent line of works proposes to study over-parameterized QNNs by examining a quantum version of tangent kernels. In this work, we study the dynamics of QNNs and show that contrary to popular belief it is qualitatively different from that of any kernel regression: due to the unitarity of quantum operations, there is a non-negligible deviation from the tangent kernel regression derived at the random initialization. As a result of the deviation, we prove the at-most sublinear convergence for QNNs with Pauli measurements, which is beyond the explanatory power of any kernel regression dynamics. We then present the actual dynamics of QNNs in the limit of over-parameterization. The new dynamics capture the change of convergence rate during training and implies that the range of measurements is crucial to the fast QNN convergence.

This paper investigates cross-lingual temporal knowledge graph reasoning problem, which aims to facilitate reasoning on Temporal Knowledge Graphs (TKGs) in low-resource languages by transfering knowledge from TKGs in high-resource ones. The cross-lingual distillation ability across TKGs becomes increasingly crucial, in light of the unsatisfying performance of existing reasoning methods on those severely incomplete TKGs, especially in low-resource languages. However, it poses tremendous challenges in two aspects. First, the cross-lingual alignments, which serve as bridges for knowledge transfer, are usually too scarce to transfer sufficient knowledge between two TKGs. Second, temporal knowledge discrepancy of the aligned entities, especially when alignments are unreliable, can mislead the knowledge distillation process. We correspondingly propose a mutually-paced knowledge distillation model MP-KD, where a teacher network trained on a source TKG can guide the training of a student network on target TKGs with an alignment module. Concretely, to deal with the scarcity issue, MP-KD generates pseudo alignments between TKGs based on the temporal information extracted by our representation module. To maximize the efficacy of knowledge transfer and control the noise caused by the temporal knowledge discrepancy, we enhance MP-KD with a temporal cross-lingual attention mechanism to dynamically estimate the alignment strength. The two procedures are mutually paced along with model training. Extensive experiments on twelve cross-lingual TKG transfer tasks in the EventKG benchmark demonstrate the effectiveness of the proposed MP-KD method.

As artificial intelligence grows more ubiquitous, its potential and the challenges it presents are coming increasingly into focus. How we balance the risks and opportunities is shaping up as one of the defining questions of our era. In much the same way that cities have emerged as hubs of innovation in culture, politics, and commerce, so they are defining the frontiers of AI governance. Some examples of how cities have been taking the lead include the Cities Coalition for Digital Rights, the Montreal Declaration for Responsible AI, and the Open Dialogue on AI Ethics. Others can be found in San Francisco's ban of facial-recognition technology, and New York City's push for regulating the sale of automated hiring systems and creation of an algorithms management and policy officer.

There is an enormous demand,

This story is part of Future Tense Fiction, a monthly series of short stories from Future Tense and Arizona State University's Center for Science and the Imagination about how technology and science will change our lives. Amanda sat at her desk, picking at the same $30 Little Gem salad she ordered daily, suffering a small burning sensation in her gut that was triggered either by acid reflux or the dying embers of her rapidly expiring conscience. Of course, it was standard procedure for her husband to demand that the security firm Dark Metal surveil potential new hires for any of his multibillion-dollar companies, but this was the first time Amanda had been involved in contracting the private intelligence agency herself. Seedlings is your venture, Reid had promised her, even though he'd named himself CEO. I want you to take the lead on this. Amanda was COO of Seedlings and reported to her husband, who dismissed Amanda's concerns about the legal ramifications of their actions. Worrying about the law was something poor people did, Reid insisted. Besides, she'd never seen Reid do anything that nefarious with this type of information. But Maggie Everett was the type of candidate that pleased Reid. Amanda had done her job, which was to find Maggie, and the people at Dark Metal had done theirs, which was to surveil her and create a comprehensive biographical profile. This seemed like overkill to Amanda. Maggie wasn't in the running to become a high-profile executive at one of Reid's billion-dollar firms. She was being interviewed to work at a preschool. Certainly, Seedlings differed from other private preschools--there was the possibility Maggie would be exposed to confidential information. But this was what NDAs were for. Unleashing a network of spies upon a poor teacher who would ultimately be responsible for 10 toddlers seemed like an absurd waste of resources. And this was just Phase 1. Phase 2 would have to wait until after Maggie was hired, of course. Amanda reopened Dark Metal's inch-thick dossier. The logline: Maggie was smart but stupid. Smart: She'd majored in English at Yale, then received an MFA in creative writing from Brown, and finally a master's in early childhood education from Columbia. Stupid: She'd accumulated $103,345 in student debt, which she'd never pay off unless she took a job somewhere like Seedlings.

STR's Analytics division researches and develops advanced analytics and machine learning-based solutions to solve challenging problems related to national security. Our team consists of passionate and motivated engineers with advanced degrees in engineering, computer science, mathematics, and data science, who are seeking opportunities to use their deep technical knowledge and creativity to tackle some of the hardest problems that our customers face. Our projects span multiple different data modalities and incorporate advanced algorithms, deep learning, and statistical techniques to uncover patterns in social media, structured and unstructured text, time series, geospatial, and imagery data, and must operate under challenging constraints not typically found in the commercial world. The tools and technologies we develop have real world impact and US Government analysts use them to extract and enrich intelligence information around the globe. As a Machine Learning Researcher, you will utilize State of the Art (SOTA) deep learning methods to work with disparate and unlabeled multimodal data sources to create a knowledge engine that can be easily queried by humans.

European Union lawmakers are on track to ban the use of remote biometric surveillance for general law enforcement purposes. However that hasn't stopped parliamentarians in France voting to deploy AI to monitor public spaces for suspicious behavior during the 2024 Paris Olympics. On Thursday the parliament approved a plan to use automated behavioral surveillance of public spaces during the games, ignoring objections from around 40 MPs who had penned an open letter denouncing the proposal. The vote followed an earlier approval by the French Senate. The 2024 Olympics Games are due to take place in Paris between July 26 and August 11.

The education and learning system has undergone significant changes since the outbreak of Covid-19. Online learning has become more prevalent as many schools and universities have shifted their classes online, using video conferencing and other digital tools to deliver instruction. Since the pandemic, some institutions have adopted a hybrid approach, combining both online and in-person teaching. This has led to an increased reliance on technology in the classroom, and professors have had to learn how to use new technology tools, including AI platforms, to effectively teach in an online environment. And these AI, and other emerging technologies,systems are incredibly important when we talk about security of the learning space.