Search

Autonomous vehicles (AVs) are poised to revolutionize modern transportation, offering enhanced safety, efficiency, and convenience. However, the increasing complexity and connectivity of AV systems introduce significant cybersecurity challenges. This paper provides a comprehensive survey of AV security with a focus on threat modeling frameworks, including STRIDE, DREAD, and MITRE ATT\&CK, to systematically identify and mitigate potential risks. The survey examines key components of AV architectures, such as sensors, communication modules, and electronic control units (ECUs), and explores common attack vectors like wireless communication exploits, sensor spoofing, and firmware vulnerabilities. Through case studies of real-world incidents, such as the Jeep Cherokee and Tesla Model S exploits, the paper highlights the critical need for robust security measures. Emerging technologies, including blockchain for secure Vehicle-to-Everything (V2X) communication, AI-driven threat detection, and secure Over-The-Air (OTA) updates, are discussed as potential solutions to mitigate evolving threats. The paper also addresses legal and ethical considerations, emphasizing data privacy, user safety, and regulatory compliance. By combining threat modeling frameworks, multi-layered security strategies, and proactive defenses, this survey offers insights and recommendations for enhancing the cybersecurity of autonomous vehicles.

Let $[n]$ be a finite chain $\{1, 2, \ldots, n\}$, and let $\mathcal{LS}_{n}$ be the semigroup consisting of all isotone and order-decreasing partial transformations on $[n]$. Moreover, let $\mathcal{SS}_{n} = \{\alpha \in \mathcal{LS}_{n} : \, 1 \in \text{Dom } \alpha\}$ be the subsemigroup of $\mathcal{LS}_{n}$, consisting of all transformations in $\mathcal{LS}_{n}$ each of whose domain contains $1$. For $1 \leq p \leq n$, let $K(n,p) = \{\alpha \in \mathcal{LS}_{n} : \, |\text{Im } \, \alpha| \leq p\}$ and $M(n,p) = \{\alpha \in \mathcal{SS}_{n} : \, |\text{Im } \alpha| \leq p\}$ be the two-sided ideals of $\mathcal{LS}_{n}$ and $\mathcal{SS}_{n}$, respectively. Furthermore, let ${RLS}_{n}(p)$ and ${RSS}_{n}(p)$ denote the Rees quotients of $K(n,p)$ and $M(n,p)$, respectively. It is shown in this article that for any $S \in \{\mathcal{SS}_{n}, \mathcal{LS}_{n}, {RLS}_{n}(p), {RSS}_{n}(p)\}$, $S$ is abundant and idempotent generated for all values of $n$. Moreover, the ranks of the Rees quotients ${RLS}_{n}(p)$ and ${RSS}_{n}(p)$ are shown to be equal to the ranks of the two-sided ideals $K(n,p)$ and $M(n,p)$, respectively. Finally, these ranks are computed to be $\sum\limits_{k=p}^{n} \binom{n}{k} \binom{k-1}{p-1}$ and $\binom{n-1}{p-1}2^{n-p}$, respectively.

In the context of communication complexity, we explore randomized protocols for graph coloring, focusing specifically on the vertex and edge coloring problems in $n$-vertex graphs $G$ with a maximum degree $\Delta$. We consider a scenario where the edges of $G$ are partitioned between two players. Our first contribution is a randomized protocol that efficiently finds a $(\Delta + 1)$-vertex coloring of $G$, utilizing $O(n)$ bits of communication in expectation and completing in $O(\log \log n \cdot \log \Delta)$ rounds in the worst case. This advancement represents a significant improvement over the work of Flin and Mittal [PODC 2024], who achieved the same communication cost but required $O(n)$ rounds in expectation, thereby making a significant reduction in the round complexity. We also present a randomized protocol for a $(2\Delta - 1)$-edge coloring of $G$, which maintains the same $O(n)$ bits of communication in expectation over $O(\log^\ast \Delta)$ rounds in the worst case. We complement the result with a tight $\Omega(n)$-bit lower bound on the communication complexity of the $(2\Delta-1)$-edge coloring, while a similar $\Omega(n)$ lower bound for the $(\Delta+1)$-vertex coloring has been established by Flin and Mittal [PODC 2024].

We introduce a novel approach for detecting distribution shifts that negatively impact the performance of machine learning models in continuous production environments, which requires no access to ground truth data labels. It builds upon the work of Podkopaev and Ramdas [2022], who address scenarios where labels are available for tracking model errors over time. Our solution extends this framework to work in the absence of labels, by employing a proxy for the true error. This proxy is derived using the predictions of a trained error estimator. Experiments show that our method has high power and false alarm control under various distribution shifts, including covariate and label shifts and natural shifts over geography and time., Comment: Accepted at the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

We present phi-4, a 14-billion parameter language model developed with a training recipe that is centrally focused on data quality. Unlike most language models, where pre-training is based primarily on organic data sources such as web content or code, phi-4 strategically incorporates synthetic data throughout the training process. While previous models in the Phi family largely distill the capabilities of a teacher model (specifically GPT-4), phi-4 substantially surpasses its teacher model on STEM-focused QA capabilities, giving evidence that our data-generation and post-training techniques go beyond distillation. Despite minimal changes to the phi-3 architecture, phi-4 achieves strong performance relative to its size -- especially on reasoning-focused benchmarks -- due to improved data, training curriculum, and innovations in the post-training scheme.

Locally stationary processes (LSPs) provide a robust framework for modeling time-varying phenomena, allowing for smooth variations in statistical properties such as mean and variance over time. In this paper, we address the estimation of the conditional probability distribution of LSPs using Nadaraya-Watson (NW) type estimators. The NW estimator approximates the conditional distribution of a target variable given covariates through kernel smoothing techniques. We establish the convergence rate of the NW conditional probability estimator for LSPs in the univariate setting under the Wasserstein distance and extend this analysis to the multivariate case using the sliced Wasserstein distance. Theoretical results are supported by numerical experiments on both synthetic and real-world datasets, demonstrating the practical usefulness of the proposed estimators.

Galaxy mergers have been shown to trigger AGN in the nearby universe, but the timescale over which this process happens remains unconstrained. The Multi-Model Merger Identifier (MUMMI) machine vision pipeline has been demonstrated to provide reliable predictions of time post-merger (T_PM) for galaxies selected from the Ultraviolet Near Infrared and Optical Northern Survey (UNIONS) up to T_PM=1.76 Gyr after coalescence. By combining the post-mergers identified in UNIONS with pre-coalescence galaxy pairs, we can study the triggering of AGN throughout the merger sequence. AGN are identified using a range of complementary metrics: mid-IR colours, narrow emission lines and broad emission lines, which can be combined to provide insight into the demographics of dust and luminosity of the AGN population. Our main results are: 1) Regardless of the metric used, we find that the peak AGN excess (compared with a matched control sample) occurs immediately after coalescence, at 0 < T_PM < 0.16 Gyr. 2) The excess of AGN is observed until long after coalescence; both the mid-IR selected AGN and broad line AGN are more common than in the control sample even in the longest time bin of our sample (0.96 < T_PM < 1.76 Gyr). 3) The AGN excess is larger for more luminous and bolometrically dominant AGN, and we find that AGN in post-mergers are generally more luminous than secularly triggered events. 4) A deficit of broad line AGN in the pre-merger phase, that evolves into an excess in post-mergers is consistent with evolution of the covering fraction of nuclear obscuring material. Before coalescence, tidally triggered inflows increase the covering fraction of nuclear dust; in the post-merger regime feedback from the AGN clears (at least some of) this material. 5) The statistical peak in the triggering of starbursts occurs contemporaneously with AGN, within 0.16 Gyr of coalescence., Comment: Submitted to the Open Journal of Astrophysics

Despite considerable progress in stereo depth estimation, omnidirectional imaging remains underexplored, mainly due to the lack of appropriate data. We introduce Helvipad, a real-world dataset for omnidirectional stereo depth estimation, consisting of 40K frames from video sequences across diverse environments, including crowded indoor and outdoor scenes with diverse lighting conditions. Collected using two 360{\deg} cameras in a top-bottom setup and a LiDAR sensor, the dataset includes accurate depth and disparity labels by projecting 3D point clouds onto equirectangular images. Additionally, we provide an augmented training set with a significantly increased label density by using depth completion. We benchmark leading stereo depth estimation models for both standard and omnidirectional images. The results show that while recent stereo methods perform decently, a significant challenge persists in accurately estimating depth in omnidirectional imaging. To address this, we introduce necessary adaptations to stereo models, achieving improved performance., Comment: Project page: https://vita-epfl.github.io/Helvipad

Understanding future weather changes at regional and local scales is crucial for planning and decision-making, particularly in the context of extreme weather events, as well as for broader applications in agriculture, insurance, and infrastructure development. However, the computational cost of downscaling Global Climate Models (GCMs) to the fine resolutions needed for such applications presents a significant barrier. Drawing on advancements in weather forecasting models, this study introduces a cost-efficient downscaling method using a pretrained Earth Vision Transformer (Earth ViT) model. Initially trained on ERA5 data to downscale from 50 km to 25 km resolution, the model is then tested on the higher resolution BARRA-SY dataset at a 3 km resolution. Remarkably, it performs well without additional training, demonstrating its ability to generalize across different resolutions. This approach holds promise for generating large ensembles of regional climate simulations by downscaling GCMs with varying input resolutions without incurring additional training costs. Ultimately, this method could provide more comprehensive estimates of potential future changes in key climate variables, aiding in effective planning for extreme weather events and climate change adaptation strategies.

Incorporating AI technologies into digital infrastructure offers transformative potential for energy management, particularly in enhancing energy efficiency and supporting net-zero objectives. However, the complexity of IoT-generated datasets often poses a significant challenge, hindering the translation of research insights into practical, real-world applications. This paper presents the design of an interactive visualization tool, BiTSA. The tool enables building managers to interpret complex energy data quickly and take immediate, data-driven actions based on real-time insights. By integrating advanced forecasting models with an intuitive visual interface, our solution facilitates proactive decision-making, optimizes energy consumption, and promotes sustainable building management practices. BiTSA will empower building managers to optimize energy consumption, control demand-side energy usage, and achieve sustainability goals., Comment: 4 pages, 4 figures, 3 tables

Addressing the challenges of irregularity and concept drift in streaming time series is crucial in real-world predictive modelling. Previous studies in time series continual learning often propose models that require buffering of long sequences, potentially restricting the responsiveness of the inference system. Moreover, these models are typically designed for regularly sampled data, an unrealistic assumption in real-world scenarios. This paper introduces ODEStream, a novel buffer-free continual learning framework that incorporates a temporal isolation layer that integrates temporal dependencies within the data. Simultaneously, it leverages the capability of neural ordinary differential equations to process irregular sequences and generate a continuous data representation, enabling seamless adaptation to changing dynamics in a data streaming scenario. Our approach focuses on learning how the dynamics and distribution of historical data change with time, facilitating the direct processing of streaming sequences. Evaluations on benchmark real-world datasets demonstrate that ODEStream outperforms the state-of-the-art online learning and streaming analysis baselines, providing accurate predictions over extended periods while minimising performance degradation over time by learning how the sequence dynamics change.

We introduce a general definition of a $n$-crossed module of $P$-algebras over an algebraic operad $P$, which coincides with historical definitions in the cases of the operads As and Lie and $n = 1$. We establish a natural isomorphism between the abelian group of equivalence classes of $n$-crossed modules over a pair $(A,M)$ for an operad $P$ and the $(n+1)^\text{th}$ operadic cohomology group of $A$ with coefficients in $M$., Comment: 21 pages

Nature-inspired computation is receiving increasing attention. Various Ising machine implementations have recently been proven to be effective in solving numerous combinatorial optimization problems including maximum cut, low density parity check (LDPC) decoding, and Boolean satisfiability (SAT) problems. In this paper, a novel method is presented to solve SAT or MAX-SAT problems with a CMOS circuit implementation. The technique solves a SAT problem by mapping the SAT variables onto quantized capacitor voltages generated by an array of nodes that interact through a network of coupling units. The nodal interaction is achieved through coupling currents produced by the coupling units, which charge or discharge capacitor voltages, implementing a gradient descent along the SAT problem's cost function to minimize the number of unsatisfied clauses. The system also incorporates a unique low-complexity perturbation scheme to avoid settling in local minima, greatly enhancing the performance of the system. The simulation results demonstrate that the proposed SKI-SAT is a high-performance and low-energy alternative that surpasses existing solvers by significant margins, achieving more than 10 times faster solution and 300 times less power., Comment: 10 pages, 10 figures, 2 tables

Recent advancements in Large Language Models (LLMs) have significantly improved text generation capabilities, but these systems are still known to hallucinate, and granular uncertainty estimation for long-form LLM generations remains challenging. In this work, we propose Graph Uncertainty -- which represents the relationship between LLM generations and claims within them as a bipartite graph and estimates the claim-level uncertainty with a family of graph centrality metrics. Under this view, existing uncertainty estimation methods based on the concept of self-consistency can be viewed as using degree centrality as an uncertainty measure, and we show that more sophisticated alternatives such as closeness centrality provide consistent gains at claim-level uncertainty estimation. Moreover, we present uncertainty-aware decoding techniques that leverage both the graph structure and uncertainty estimates to improve the factuality of LLM generations by preserving only the most reliable claims. Compared to existing methods, our graph-based uncertainty metrics lead to an average of 6.8% relative gains on AUPRC across various long-form generation settings, and our end-to-end system provides consistent 2-4% gains in factuality over existing decoding techniques while significantly improving the informativeness of generated responses., Comment: Accepted as a Spotlight paper at NeurIPS 2024

Climate models serve as critical tools for evaluating the effects of climate change and projecting future climate scenarios. However, the reliance on numerical simulations of physical equations renders them computationally intensive and inefficient. While deep learning methodologies have made significant progress in weather forecasting, they are still unstable for climate emulation tasks. Here, we propose PACER, a lightweight 684K parameter Physics Informed Uncertainty Aware Climate Emulator. PACER emulates temperature and precipitation stably for 86 years while only being trained on greenhouse gas emissions data. We incorporate a fundamental physical law of advection-diffusion in PACER accounting for boundary conditions and empirically estimating the diffusion co-efficient and flow velocities from emissions data. PACER has been trained on 15 climate models provided by ClimateSet outperforming baselines across most of the climate models and advancing a new state of the art in a climate diagnostic task.

The growing integration of digitized infrastructure with Internet of Things (IoT) networks has transformed the management and optimization of building energy consumption. By leveraging IoT-based monitoring systems, stakeholders such as building managers, energy suppliers, and policymakers can make data-driven decisions to improve energy efficiency. However, accurate energy forecasting and analytics face persistent challenges, primarily due to the inherent physical constraints of buildings and the diverse, heterogeneous nature of IoT-generated data. In this study, we conduct a comprehensive benchmarking of two publicly available IoT datasets, evaluating the performance of time series foundation models in the context of building energy analytics. Our analysis shows that single-modal models demonstrate significant promise in overcoming the complexities of data variability and physical limitations in buildings, with future work focusing on optimizing multi-modal models for sustainable energy management., Comment: 7 pages, 1 figures, and 4 tables

Traditional POI recommendation systems often lack transparency, interpretability, and scrutability due to their reliance on dense vector-based user embeddings. Furthermore, the cold-start problem -- where systems have insufficient data for new users -- limits their ability to generate accurate recommendations. Existing methods often address this by leveraging similar trajectories from other users, but this approach can be computationally expensive and increases the context length for LLM-based methods, making them difficult to scale. To address these limitations, we propose a method that generates natural language (NL) user profiles from large-scale, location-based social network (LBSN) check-ins, utilizing robust personality assessments and behavioral theories. These NL profiles capture user preferences, routines, and behaviors, improving POI prediction accuracy while offering enhanced transparency. By incorporating NL profiles as system prompts to LLMs, our approach reduces reliance on extensive historical data, while remaining flexible, easily updated, and computationally efficient. Our method is not only competitive with other LLM-based and complex agentic frameworks but is also more scalable for real-world scenarios and on-device POI recommendations. Results demonstrate that our approach consistently outperforms baseline methods, offering a more interpretable and resource-efficient solution for POI recommendation systems. Our source code is available at: \url{https://github.com/w11wo/GenUP}.

Explainable AI (XAI) aims to support appropriate human-AI reliance by increasing the interpretability of complex model decisions. Despite the proliferation of proposed methods, there is mixed evidence surrounding the effects of different styles of XAI explanations on human-AI reliance. Interpreting these conflicting findings requires an understanding of the individual and combined qualities of different explanation styles that influence appropriate and inappropriate human-AI reliance, and the role of interpretability in this interaction. In this study, we investigate the influences of feature-based, example-based, and combined feature- and example-based XAI methods on human-AI reliance through a two-part experimental study with 274 participants comparing these explanation style conditions. Our findings suggest differences between feature-based and example-based explanation styles beyond interpretability that affect human-AI reliance patterns across differences in individual performance and task complexity. Our work highlights the importance of adapting explanations to their specific users and context over maximising broad interpretability., Comment: 20 pages

Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of fine-tuning them with RL in a specific environment. In this paper, we propose a novel framework to analyze the sensitivity of LLMs to prompt formulations following RL training in a textual environment. Our findings reveal that the performance of LLMs degrades when faced with prompt formulations different from those used during the RL training phase. Besides, we analyze the source of this sensitivity by examining the model's internal representations and salient tokens. Finally, we propose to use a contrastive loss to mitigate this sensitivity and improve the robustness and generalization capabilities of LLMs.

Climate change is negatively impacting the world's biodiversity. To build automated systems to monitor these negative biodiversity impacts, large-scale, volunteer-collected datasets like iNaturalist are built from community-identified, natural imagery. However, such volunteer-based data are opportunistic and lack a structured sampling strategy, resulting in geographic, temporal, observation quality, and socioeconomic, biases that stymie uptake of these models for downstream biodiversity monitoring tasks. Here we introduce DivShift North American West Coast (DivShift-NAWC), a curated dataset of almost 8 million iNaturalist plant images across the western coast of North America, for exploring the effects of these biases on deep learning model performance. We compare model performance across four known biases and observe that they indeed confound model performance. We suggest practical strategies for curating datasets to train deep learning models for monitoring climate change's impacts on the world's biodiversity., Comment: Accepted to NeurIPS 2024 Workshop on Tackling Climate Change with Machine Learning

Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate their understanding of such knowledge, we introduce WorldCuisines, a massive-scale benchmark for multilingual and multicultural, visually grounded language understanding. This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date. It includes tasks for identifying dish names and their origins. We provide evaluation datasets in two sizes (12k and 60k instances) alongside a training dataset (1 million instances). Our findings show that while VLMs perform better with correct location context, they struggle with adversarial contexts and predicting specific regional cuisines and languages. To support future research, we release a knowledge base with annotated food entries and images along with the VQA data., Comment: Preprint

In this work, we bridge the gap between wearable sensor technology and personalized AI assistants by enabling Large Language Models (LLMs) to understand time-series tasks like human activity recognition (HAR). Despite the strong reasoning and generalization capabilities of LLMs, leveraging them for sensor data tasks remains largely unexplored. This gap stems from challenges like the lack of semantic context in time-series data, computational limitations, and LLMs' difficulty processing numerical inputs. To address these issues, we introduce SensorLLM, a two-stage framework to unlock LLMs' potential for sensor data tasks. In the Sensor-Language Alignment Stage, we introduce special tokens for each sensor channel and automatically generate trend-descriptive text to align sensor data with textual inputs, enabling SensorLLM to capture numerical changes, channel-specific information, and sensor data of varying lengths-capabilities that existing LLMs typically struggle with, all without the need for human annotations. Next, in Task-Aware Tuning Stage, we refine the model for HAR classification using the frozen LLM and alignment module, achieving performance on par with or surpassing state-of-the-art models. We further demonstrate that SensorLLM evolves into an effective sensor learner, reasoner, and classifier through Sensor-Language Alignment, enabling it to generalize across diverse datasets for HAR tasks. We strongly believe our work lays the stepstone for future time-series and text alignment research, offering a path toward foundation models for sensor data.

While Large language model (LLM)-based programming assistants such as CoPilot and ChatGPT can help improve the productivity of professional software developers, they can also facilitate cheating in introductory computer programming courses. Assuming instructors have limited control over the industrial-strength models, this paper investigates the baseline performance of 5 widely used LLMs on a collection of introductory programming problems, examines adversarial perturbations to degrade their performance, and describes the results of a user study aimed at understanding the efficacy of such perturbations in hindering actual code generation for introductory programming assignments. The user study suggests that i) perturbations combinedly reduced the average correctness score by 77%, ii) the drop in correctness caused by these perturbations was affected based on their detectability.

Given a smooth quasi-projective complex algebraic variety $\mathcal{S}$, we prove that there are only finitely many Hodge-generic non-isotrivial families of smooth projective hypersurfaces over $\mathcal{S}$ of degree $d$ in $\mathbb{P}_{\mathbb C}^{n+1}$. We prove that the finiteness is uniform in $\mathcal{S}$ and we give examples where the result is sharp. We also prove similar results for certain complete intersections in $\mathbb{P}_{\mathbb C}^{n+1}$ of higher codimension and more generally for algebraic varieties whose moduli space admits a period map that satisfies the infinitesimal Torelli theorem.

Crisis management (CM) for critical infrastructures, natural disasters such as wildfires and hurricanes, terrorist actions, or civil unrest requires high speed communications and connectivity, and access to high performance computational resources to deliver timely dynamic responses to the crisis being managed by different first responders. CM systems should detect, recognize, and disseminate huge amounts of heterogeneous dynamic events that operate at different speeds and formats. Furthermore, the processing of crisis events and the development of real-time responses are major research challenges when the communications and computational resources needed by CM stakeholders are not available or severely degraded by the crisis. The main goal of the research presented in this paper is to utilize Unmanned Autonomous Systems (UAS) to provide Aerial-based Crisis Management Center (ACMC) that will provide the required communications services and the computational resources that are critically needed by first responders. In our approach to develop an ACMC architecture, we utilize a set of flexible Unmanned Aerial Systems (UAS) that can be dynamically composed to meet the communications and computational requirements of CM tasks. The ACMC services will be modeled as a deep neural network (DNN) mass transport approach to cover a distributed target in a decentralized manner. This is indeed a new decentralized coverage approach with time-varying communication weights. Furthermore, our analysis proves the stability and convergence of the proposed DNN-based mass transport for a team of UAS (e.g., quadcopters), where each quadcopter uses a feedback nonlinear control to independently attain the intended coverage trajectory in a decentralized manner.

Multi-objective parametric optimization problem is presented for overwrapped composite pressure vessels under internal pressure for storage and heating water. It is solved using the developed iterative optimization algorithm. Optimal values of design parameters for the vessel are obtained by varying the set of parameters for composite layers, such as the thickness of layers and radii of polar openings, which influence the distribution of fiber angles along the vessel. The suggested optimization methodology is based on the mechanical solution for composite vessels and the satisfaction of the main failure criteria. An innovative approach lies in the possibility of using the developed optimization methodology for designing vessels with non-symmetrical filament winding, which have unequal polar openings on the domes. This became possible due to the development of a special numerical mechanical finite element model of a composite vessel. A specific Python program provides the creation of a model and controls the exchange of data between the modules of the iterative optimization process. The numerical model includes the determination of the distribution of fiber angles on the domes and cylindrical part of the vessel as well as changes in layer thicknesses. The optimization problem solution is provided using a Multi-Island Genetic Algorithm, this type of method showed its efficiency for such applications, by allowing to avoid local solutions. Thus, optimal parameters of a composite vessel were found by minimizing composite mass and thickness and maximizing the strain energy. Test solutions using the developed methodology are presented for three types of composite materials to evaluate their possibility for integration into the vessel design model.

Deploying machine learning (ML) in dynamic data-driven applications systems (DDDAS) can improve the security of industrial control systems (ICS). However, ML-based DDDAS are vulnerable to adversarial attacks because adversaries can alter the input data slightly so that the ML models predict a different result. In this paper, our goal is to build a resilient edge machine learning (reML) architecture that is designed to withstand adversarial attacks by performing Data Air Gap Transformation (DAGT) to anonymize data feature spaces using deep neural networks and randomize the ML models used for predictions. The reML is based on the Resilient DDDAS paradigm, Moving Target Defense (MTD) theory, and TinyML and is applied to combat adversarial attacks on ICS. Furthermore, the proposed approach is power-efficient and privacy-preserving and, therefore, can be deployed on power-constrained devices to enhance ICS security. This approach enables resilient ML inference at the edge by shifting the computation from the computing-intensive platforms to the resource-constrained edge devices. The incorporation of TinyML with TensorFlow Lite ensures efficient resource utilization and, consequently, makes reML suitable for deployment in various industrial control environments. Furthermore, the dynamic nature of reML, facilitated by the resilient DDDAS development environment, allows for continuous adaptation and improvement in response to emerging threats. Lastly, we evaluate our approach on an ICS dataset and demonstrate that reML provides a viable and effective solution for resilient ML inference at the edge devices., Comment: Accepted by Dynamic Data Driven Applications Systems: International Conference, DDDAS, Springer. 2024

The complementary information found in different modalities of patient data can aid in more accurate modelling of a patient's disease state and a better understanding of the underlying biological processes of a disease. However, the analysis of multi-modal, multi-omics data presents many challenges, including high dimensionality and varying size, statistical distribution, scale and signal strength between modalities. In this work we compare the performance of a variety of ensemble machine learning algorithms that are capable of late integration of multi-class data from different modalities. The ensemble methods and their variations tested were i) a voting ensemble, with hard and soft vote, ii) a meta learner, iii) a multi-modal Adaboost model using a hard vote, a soft vote and a meta learner to integrate the modalities on each boosting round, the PB-MVBoost model and a novel application of a mixture of experts model. These were compared to simple concatenation as a baseline. We examine these methods using data from an in-house study on hepatocellular carcinoma (HCC), along with four validation datasets on studies from breast cancer and irritable bowel disease (IBD). Using the area under the receiver operating curve as a measure of performance we develop models that achieve a performance value of up to 0.85 and find that two boosted methods, PB-MVBoost and Adaboost with a soft vote were the overall best performing models. We also examine the stability of features selected, and the size of the clinical signature determined. Finally, we provide recommendations for the integration of multi-modal multi-class data., Comment: 21 pages, 5 figures

Plastic waste in aquatic environments poses severe risks to marine life and human health. Autonomous robots can be utilized to collect floating waste, but they require accurate object identification capability. While deep learning has been widely used as a powerful tool for this task, its performance is significantly limited by outdoor light conditions and water surface reflection. Light polarization, abundant in such environments yet invisible to the human eye, can be captured by modern sensors to significantly improve litter detection accuracy on water surfaces. With this goal in mind, we introduce PoTATO, a dataset containing 12,380 labeled plastic bottles and rich polarimetric information. We demonstrate under which conditions polarization can enhance object detection and, by providing raw image data, we offer an opportunity for the research community to explore novel approaches and push the boundaries of state-of-the-art object detection algorithms even further. Code and data are publicly available at https://github.com/luisfelipewb/ PoTATO/tree/eccv2024., Comment: ECCV24 TRICKY workshop, Sep 2024, Milano (Italy), Italy

Privacy is dynamic, sensitive, and contextual, much like our emotions. Previous studies have explored the interplay between privacy and context, privacy and emotion, and emotion and context. However, there remains a significant gap in understanding the interplay of these aspects simultaneously. In this paper, we present a preliminary study investigating the role of emotions in driving individuals' information sharing behaviour, particularly in relation to urban locations and social ties. We adopt a novel methodology that integrates context (location and time), emotion, and personal information sharing behaviour, providing a comprehensive analysis of how contextual emotions affect privacy. The emotions are assessed with both self-reporting and electrodermal activity (EDA). Our findings reveal that self-reported emotions influence personal information-sharing behaviour with distant social groups, while neutral emotions lead individuals to share less precise information with close social circles, a pattern is potentially detectable with wrist-worn EDA. Our study helps lay the foundation for personalised emotion-aware strategies to mitigate oversharing risks and enhance user privacy in the digital age., Comment: see https://doi.org/10.1145/3675094.3677598

We present the CO(1-0) maps of 28 infrared-bright galaxies from the Great Observatories All-Sky Luminous Infrared Galaxy Survey (GOALS) taken with the Combined Array for Research in Millimeter Astronomy (CARMA). We detect 100GHz continuum in 16 of 28 galaxies, which trace both active galactic nuclei (AGNs) and compact star-forming cores. The GOALS galaxies show a variety of molecular gas morphologies, though in the majority of cases, the average velocity fields show a gradient consistent with rotation. We fit the full continuum SEDs of each of the source using either MAGPHYS or SED3FIT (if there are signs of an AGN) to derive the total stellar mass, dust mass, and star formation rates of each object. We adopt a value determined from luminous and ultraluminous infrared galaxies (LIRGs and ULIRGs) of $\alpha_{\rm CO}=1.5^{+1.3}_{-0.8}~M_\odot$ (K km s$^{-1}$ pc$^2)^{-1}$, which leads to more physical values for $f_{\rm mol}$ and the gas-to-dust ratio. Mergers tend to have the highest gas-to-dust ratios. We assume the cospatiality of the molecular gas and star formation, and plot the sample on the Schmidt-Kennicutt relation, we find that they preferentially lie above the line set by normal star-forming galaxies. This hyper-efficiency is likely due to the increased turbulence in these systems, which decreases the freefall time compared to star-forming galaxies, leading to "enhanced" star formation efficiency. Line wings are present in a non-negligible subsample (11/28) of the CARMA GOALS sources and are likely due to outflows driven by AGNs or star formation, gas inflows, or additional decoupled gas components., Comment: 29 pages, 4 tables, 11 figures, Accepted by the Astrophysical Journal

Chiral magnets have garnered significant interest due to the emergence of unique phenomena prohibited in inversion-symmetric magnets. While the equilibrium characteristics of chiral magnets have been extensively explored through the Dzyaloshinskii-Moriya interaction (DMI), non-equilibrium properties like magnetic damping have received comparatively less attention. We present the inaugural direct observation of chiral damping through Brillouin light scattering (BLS) spectroscopy. Employing BLS spectrum analysis, we independently deduce the Dzyaloshinskii-Moriya interaction (DMI) and chiral damping, extracting them from the frequency shift and linewidth of the spectrum peak, respectively. The resulting linewidths exhibit clear odd symmetry with respect to the magnon wave vector, unambiguously confirming the presence of chiral damping. Our study introduces a novel methodology for quantifying chiral damping, with potential ramifications on diverse nonequilibrium phenomena within chiral magnets.

Clients wishing to implement generative AI in the domain of IT Support and AIOps face two critical issues: domain coverage and model size constraints due to model choice limitations. Clients might choose to not use larger proprietary models such as GPT-4 due to cost and privacy concerns and so are limited to smaller models with potentially less domain coverage that do not generalize to the client's domain. Retrieval augmented generation is a common solution that addresses both of these issues: a retrieval system first retrieves the necessary domain knowledge which a smaller generative model leverages as context for generation. We present a system developed for a client in the IT Support domain for support case solution recommendation that combines retrieval augmented generation (RAG) for answer generation with an encoder-only model for classification and a generative large language model for query generation. We cover architecture details, data collection and annotation, development journey and preliminary validations, expected final deployment process and evaluation plans, and finally lessons learned., Comment: 7 pages, 3 figures, 6 tables