Search

This study presents a deep learning approach to predicting structural and electronic properties of materials using Graph Neural Networks (GNNs). Leveraging data from the Materials Project database, we construct graph representations of crystal structures and employ GNNs to predict multiple properties simultaneously. All crystal structures are from the Materials Project database, with a total of 158,874 structures used. Our model achieves high predictive accuracy across various properties, as indicated by \( R^2 \) values: 0.96 for density, 0.97 for formation energy, 0.54 for energy above hull, 0.47 for structural stability (is\_S), 0.76 for band gap, 0.86 for valence band maximum, 0.78 for conduction band minimum, and 0.82 for Fermi energy. These results demonstrate the potential of GNNs in materials science, offering a powerful tool for rapid screening and discovery of materials with desired properties., Comment: 9 pages

We present a simple toy model of cosmic acceleration driven purely by a self-interacting scalar field embedded in theory of grand unification. The scalar self-interaction is Higgs-like and provokes a spontaneous symmetry breaking. The coefficient of the quadratic term in the self-interaction potential has an evolution and it leads to a cosmic variation of proton-to-electron mass ratio, $\mu$. We perform a cosmological reconstruction from the kinematic parameter jerk and discuss a few cosmological consequences of the theory. We also compare the theoretically calculated $\mu$ variation with the observations of molecular absorption spectra from Cesium Atomic Clock data., Comment: 9 Pages, 10 Figures, comments are welcome

Piezoelectricity, the generation of electric charge in response to mechanical stress, is a key property in both natural and synthetic materials. This study significantly boosts the piezoelectric response of chitosan, a biodegradable biopolymer, by integrating chitin/chitosan nanocrystals into natural chitosan-based thin film elastomers. The resulting materials achieve d$_{33}$ values of 15-19 pmV$^{-1}$, a marked improvement over the 5-9 pmV$^{-1}$ observed in pure chitosan films thanks to increased crystallinity from the nanocrystals. We utilize piezoresponse force microscopy (PFM) to accurately measure the d$_{33}$ coefficient, employing an engineered extraction method that eliminates the electrostatic contribution, which can overestimate the piezoelectric response. The resulting chitosan elastomers exhibit elastic deformation up to 40\% strain and a Young's modulus of approximately 100 MPa, similar to soft tissues. These properties, along with the fact that the employed materials can be entirely crafted from upcycled biowaste, make these elastomers ideal for prosthetics, wearable devices, energy harvesters, and sustainable transducers. Our findings underscore the potential of chitosan-based piezoelectric materials for advanced applications in biotechnology, soft robotics, and the green Internet of Things.

Differentially Private Stochastic Gradient Descent (DP-SGD) is a popular iterative algorithm used to train machine learning models while formally guaranteeing the privacy of users. However, the privacy analysis of DP-SGD makes the unrealistic assumption that all intermediate iterates (aka internal state) of the algorithm are released since, in practice, only the final trained model, i.e., the final iterate of the algorithm is released. In this hidden state setting, prior work has provided tighter analyses, albeit only when the loss function is constrained, e.g., strongly convex and smooth or linear. On the other hand, the privacy leakage observed empirically from hidden state DP-SGD, even when using non-convex loss functions, suggests that there is in fact a gap between the theoretical privacy analysis and the privacy guarantees achieved in practice. Therefore, it remains an open question whether hidden state privacy amplification for DP-SGD is possible for all (possibly non-convex) loss functions in general. In this work, we design a counter-example and show, both theoretically and empirically, that a hidden state privacy amplification result for DP-SGD for all loss functions in general is not possible. By carefully constructing a loss function for DP-SGD, we show that for specific loss functions, the final iterate of DP-SGD alone leaks as much information as the sequence of all iterates combined. Furthermore, we empirically verify this result by evaluating the privacy leakage from the final iterate of DP-SGD with our loss function and show that this exactly matches the theoretical upper bound guaranteed by DP. Therefore, we show that the current privacy analysis for DP-SGD is tight for general loss functions and conclude that no privacy amplification is possible for DP-SGD in general for all (possibly non-convex) loss functions.

Synthetic data created by differentially private (DP) generative models is increasingly used in real-world settings. In this context, PATE-GAN has emerged as a popular algorithm, combining Generative Adversarial Networks (GANs) with the private training approach of PATE (Private Aggregation of Teacher Ensembles). In this paper, we analyze and benchmark six open-source PATE-GAN implementations, including three by (a subset of) the original authors. First, we shed light on architecture deviations and empirically demonstrate that none replicate the utility performance reported in the original paper. Then, we present an in-depth privacy evaluation, including DP auditing, showing that all implementations leak more privacy than intended and uncovering 17 privacy violations and 5 other bugs. Our codebase is available from https://github.com/spalabucr/pategan-audit.

This paper presents an auditing procedure for the Differentially Private Stochastic Gradient Descent (DP-SGD) algorithm in the black-box threat model that is substantially tighter than prior work. The main intuition is to craft worst-case initial model parameters, as DP-SGD's privacy analysis is agnostic to the choice of the initial model parameters. For models trained on MNIST and CIFAR-10 at theoretical $\varepsilon=10.0$, our auditing procedure yields empirical estimates of $\varepsilon_{emp} = 7.21$ and $6.95$, respectively, on a 1,000-record sample and $\varepsilon_{emp}= 6.48$ and $4.96$ on the full datasets. By contrast, previous audits were only (relatively) tight in stronger white-box models, where the adversary can access the model's inner parameters and insert arbitrary gradients. Overall, our auditing procedure can offer valuable insight into how the privacy analysis of DP-SGD could be improved and detect bugs and DP violations in real-world implementations. The source code needed to reproduce our experiments is available at https://github.com/spalabucr/bb-audit-dpsgd., Comment: To appear in the Proceedings of the Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024). Please cite accordingly

Differentially private synthetic data generation (DP-SDG) algorithms are used to release datasets that are structurally and statistically similar to sensitive data while providing formal bounds on the information they leak. However, bugs in algorithms and implementations may cause the actual information leakage to be higher. This prompts the need to verify whether the theoretical guarantees of state-of-the-art DP-SDG implementations also hold in practice. We do so via a rigorous auditing process: we compute the information leakage via an adversary playing a distinguishing game and running membership inference attacks (MIAs). If the leakage observed empirically is higher than the theoretical bounds, we identify a DP violation; if it is non-negligibly lower, the audit is loose. We audit six DP-SDG implementations using different datasets and threat models and find that black-box MIAs commonly used against DP-SDGs are severely limited in power, yielding remarkably loose empirical privacy estimates. We then consider MIAs in stronger threat models, i.e., passive and active white-box, using both existing and newly proposed attacks. Overall, we find that, currently, we do not only need white-box MIAs but also worst-case datasets to tightly estimate the privacy leakage from DP-SDGs. Finally, we show that our automated auditing procedure finds both known DP violations (in 4 out of the 6 implementations) as well as a new one in the DPWGAN implementation that was successfully submitted to the NIST DP Synthetic Data Challenge. The source code needed to reproduce our experiments is available from https://github.com/spalabucr/synth-audit., Comment: To appear at Usenix Security 2024

This research introduces an innovative AI-driven precision agriculture system, leveraging YOLOv8 for disease identification and Retrieval Augmented Generation (RAG) for context-aware diagnosis. Focused on addressing the challenges of diseases affecting the coffee production sector in Karnataka, The system integrates sophisticated object detection techniques with language models to address the inherent constraints associated with Large Language Models (LLMs). Our methodology not only tackles the issue of hallucinations in LLMs, but also introduces dynamic disease identification and remediation strategies. Real-time monitoring, collaborative dataset expansion, and organizational involvement ensure the system's adaptability in diverse agricultural settings. The effect of the suggested system extends beyond automation, aiming to secure food supplies, protect livelihoods, and promote eco-friendly farming practices. By facilitating precise disease identification, the system contributes to sustainable and environmentally conscious agriculture, reducing reliance on pesticides. Looking to the future, the project envisions continuous development in RAG-integrated object detection systems, emphasizing scalability, reliability, and usability. This research strives to be a beacon for positive change in agriculture, aligning with global efforts toward sustainable and technologically enhanced food production., Comment: 6 pages, 3 figures

We performed large-scale molecular dynamics simulations based on a machine-learning force field (MLFF) to investigate the Li-ion transport mechanism in cation-disordered Li$_3$TiCl$_6$ cathode at six different temperatures, ranging from 25$^\mathrm{o}$C to 100$^\mathrm{o}$C. In this work, deep neural network method and data generated by $ab-initio$ molecular dynamics (AIMD) simulations were deployed to build a high-fidelity MLFF. Radial distribution functions, Li-ion mean square displacements (MSD), diffusion coefficients, ionic conductivity, activation energy, and crystallographic direction-dependent migration barriers were calculated and compared with corresponding AIMD and experimental data to benchmark the accuracy of the MLFF. From MSD analysis, we captured both the self and distinct parts of Li-ion dynamics. The latter reveals that the Li-ions are involved in anti-correlation motion that was rarely reported for solid-state materials. Similarly, the self and distinct parts of Li-ion dynamics were used to determine Haven's ratio to describe the Li-ion transport mechanism in Li$_3$TiCl$_6$. Obtained trajectory from molecular dynamics infers that the Li-ion transportation is mainly through interstitial hopping which was confirmed by intra- and inter-layer Li-ion displacement with respect to simulation time. Ionic conductivity (1.06 mS/cm) and activation energy (0.29eV) calculated by our simulation are highly comparable with that of experimental values. Overall, the combination of machine-learning methods and AIMD simulations explains the intricate electrochemical properties of the Li$_3$TiCl$_6$ cathode with remarkably reduced computational time. Thus, our work strongly suggests that the deep neural network-based MLFF could be a promising method for large-scale complex materials., Comment: 8 pages with 6 figures

In the contemporary digital era, the Internet functions as an unparalleled catalyst, dismantling geographical and linguistic barriers particularly evident in texting. This evolution facilitates global communication, transcending physical distances and fostering dynamic cultural exchange. A notable trend is the widespread use of transliteration, where the English alphabet is employed to convey messages in native languages, posing a unique challenge for language technology in accurately detecting the source language. This paper addresses this challenge through a dataset of phone text messages in Hindi and Russian transliterated into English utilizing BERT for language classification and Google Translate API for transliteration conversion. The research pioneers innovative approaches to identify and convert transliterated text, navigating challenges in the diverse linguistic landscape of digital communication. Emphasizing the pivotal role of comprehensive datasets for training Large Language Models LLMs like BERT, our model showcases exceptional proficiency in accurately identifying and classifying languages from transliterated text. With a validation accuracy of 99% our models robust performance underscores its reliability. The comprehensive exploration of transliteration dynamics supported by innovative approaches and cutting edge technologies like BERT, positions our research at the forefront of addressing unique challenges in the linguistic landscape of digital communication. Beyond contributing to language identification and transliteration capabilities this work holds promise for applications in content moderation, analytics and fostering a globally connected community engaged in meaningful dialogue., Comment: 4 Pages, 6 diagrams

As evidenced by recent survey results, majority of asteroids are slow rotators (P>12 h), but lack spin and shape models due to selection bias. This bias is skewing our overall understanding of the spins, shapes, and sizes of asteroids, as well as of their other properties. Also, diameter determinations for large (>60km) and medium-sized asteroids (between 30 and 60 km) often vary by over 30% for multiple reasons. Our long-term project is focused on a few tens of slow rotators with periods of up to 60 hours. We aim to obtain their full light curves and reconstruct their spins and shapes. We also precisely scale the models, typically with an accuracy of a few percent. We used wide sets of dense light curves for spin and shape reconstructions via light-curve inversion. Precisely scaling them with thermal data was not possible here because of poor infrared data: large bodies are too bright for WISE mission. Therefore, we recently launched a campaign among stellar occultation observers, to scale these models and to verify the shape solutions, often allowing us to break the mirror pole ambiguity. The presented scheme resulted in shape models for 16 slow rotators, most of them for the first time. Fitting them to stellar occultations resolved previous inconsistencies in size determinations. For around half of the targets, this fitting also allowed us to identify a clearly preferred pole solution, thus removing the ambiguity inherent to light-curve inversion. We also address the influence of the uncertainty of the shape models on the derived diameters. Overall, our project has already provided reliable models for around 50 slow rotators. Such well-determined and scaled asteroid shapes will, e.g. constitute a solid basis for density determinations when coupled with mass information. Spin and shape models continue to fill the gaps caused by various biases., Comment: Accepted to Astronomy & Astrophysics. 12 pages + appendices

On 12 December 2023, the star $\alpha$ Orionis (Betelgeuse) will be occulted by the asteroid (319) Leona. This represents an extraordinary and unique opportunity to analyze the diameter and brightness distribution of Betelgeuse's photosphere with extreme angular resolution by studying the light curve as the asteroid occults the star from different points on Earth and at different wavelengths. Here we present observations of another occultation by Leona on 13 September 2023 to determine its projected shape and size in preparation for the December 12th event. The occultation observation campaign was highly successful. The effective diameter in projected area derived from the positive detections at 17 sites turned out to be 66 km $\pm$ 2 km using an elliptical fit to the instantaneous limb. The body is highly elongated, with dimensions of 79.6 $\pm$ 2.2 km x 54.8 $\pm$ 1.3 km in its long and short axis, respectively, at the occultation time. Also, an accurate position coming from the occultation, to improve the orbit determination of Leona for December 12 is provided., Comment: Two figures. Letter submitted to A&A

The Directorate General for Parliamentary Research Services of the European Parliament has prepared a report to the Members of the European Parliament where they enumerate seven main risks of Artificial Intelligence (AI) in medicine and healthcare: patient harm due to AI errors, misuse of medical AI tools, bias in AI and the perpetuation of existing inequities, lack of transparency, privacy and security issues, gaps in accountability, and obstacles in implementation. In this study, we propose fourteen functional requirements that AI systems may implement to reduce the risks associated with their medical purpose: AI passport, User management, Regulation check, Academic use only disclaimer, data quality assessment, Clinicians double check, Continuous performance evaluation, Audit trail, Continuous usability test, Review of retrospective/simulated cases, Bias check, eXplainable AI, Encryption and use of field-tested libraries, and Semantic interoperability. Our intention here is to provide specific high-level specifications of technical solutions to ensure continuous good performance and use of AI systems to benefit patients in compliance with the future EU regulatory framework., Comment: 14 pages, 1 figure, 1 table

From its conception, 6G is being designed with a particular focus on sustainability. The general philosophy of the H2020 Hexa-X project work on sustainability in 6G is based on two principles: to reduce direct negative life cycle impacts of 6G systems as much as possible (Sustainable 6G) and to analyze use cases that maximize positive environmental, social, and economic effects in other sectors of society (6G for Sustainability or its enablement effect). To apply this philosophy, Hexa-X is designing 6G with three sustainability objectives in mind: to enable the reduction of emissions in 6G-powered sectors of society, to reduce the total cost of ownership and to improve energy efficiency. This paper describes these objectives, their associated KPIs and quantitative targets, and the levers to reach them. Furthermore, to maximize the positive effects of 6G through the enablement effect, a link between 6G and the United Nations' Sustainable Development Goals (UN SDGs) framework is proposed and illustrated by Hexa-X use case families., Comment: IEEE ICC 2023 Second International Workshop on Green and Sustainable Networking (GreenNet), May 2023, Rome, Italy