Search

Over the recent years, the protection of the so-called `soft-targets', i.e. locations easily accessible by the general public with relatively low, though, security measures, has emerged as a rather challenging and increasingly important issue. The complexity and seriousness of this security threat growths nowadays exponentially, due to the emergence of new advanced technologies (e.g. Artificial Intelligence (AI), Autonomous Vehicles (AVs), 3D printing, etc.); especially when it comes to large-scale, popular and diverse public spaces. In this paper, a novel Digital Twin-as-a-Security-Service (DTaaSS) architecture is introduced for holistically and significantly enhancing the protection of public spaces (e.g. metro stations, leisure sites, urban squares, etc.). The proposed framework combines a Digital Twin (DT) conceptualization with additional cutting-edge technologies, including Internet of Things (IoT), cloud computing, Big Data analytics and AI. In particular, DTaaSS comprises a holistic, real-time, large-scale, comprehensive and data-driven security solution for the efficient/robust protection of public spaces, supporting: a) data collection and analytics, b) area monitoring/control and proactive threat detection, c) incident/attack prediction, and d) quantitative and data-driven vulnerability assessment. Overall, the designed architecture exhibits increased potential in handling complex, hybrid and combined threats over large, critical and popular soft-targets. The applicability and robustness of DTaaSS is discussed in detail against representative and diverse real-world application scenarios, including complex attacks to: a) a metro station, b) a leisure site, and c) a cathedral square.

Reliability is necessary in safety-critical applications spanning numerous domains. Conventional hardware-based fault tolerance techniques, such as component redundancy, ensure reliability, typically at the expense of significantly increased power consumption, and almost double (or more) hardware area. To mitigate these costs, microarchitectural fault tolerance methods try to lower overheads by leveraging microarchitectural insights, but prior evaluations focus primarily on only application performance. As different safety-critical applications prioritize different requirements beyond reliability, evaluating only limited metrics cannot guarantee that microarchitectural methods are practical and usable for all different application scenarios. To this end, in this work, we extensively characterize and compare three fault detection methods, each representing a different major fault detection category, considering real requirements from diverse application settings and employing various important metrics such as design area, power, performance overheads and latency in detection. Through this analysis, we provide important insights which may guide designers in applying the most effective fault tolerance method tailored to specific needs, advancing the overall understanding and development of robust computing systems. For this, we study three methods for hardware error detection within a processor, i.e., (i) Dual Modular Redundancy (DMR) as a conventional method, and (ii) Redundant Multithreading (R-SMT) and (iii) Parallel Error Detection (ParDet) as microarchitecture-level methods. We demonstrate that microarchitectural fault tolerance, i.e., R-SMT and ParDet, is comparably robust compared to conventional approaches (DMR), however, still exhibits unappealing trade-offs for specific real-world use cases, thus precluding their usage in certain application scenarios.

Out-of-context (OOC) misinformation poses a significant challenge in multimodal fact-checking, where images are paired with texts that misrepresent their original context to support false narratives. Recent research in evidence-based OOC detection has seen a trend towards increasingly complex architectures, incorporating Transformers, foundation models, and large language models. In this study, we introduce a simple yet robust baseline, which assesses MUltimodal SimilaritiEs (MUSE), specifically the similarity between image-text pairs and external image and text evidence. Our results demonstrate that MUSE, when used with conventional classifiers like Decision Tree, Random Forest, and Multilayer Perceptron, can compete with and even surpass the state-of-the-art on the NewsCLIPpings and VERITE datasets. Furthermore, integrating MUSE in our proposed "Attentive Intermediate Transformer Representations" (AITR) significantly improved performance, by 3.3% and 7.5% on NewsCLIPpings and VERITE, respectively. Nevertheless, the success of MUSE, relying on surface-level patterns and shortcuts, without examining factuality and logical inconsistencies, raises critical questions about how we define the task, construct datasets, collect external evidence and overall, how we assess progress in the field. We release our code at: https://github.com/stevejpapad/outcontext-misinfo-progress

We demonstrate that all perturbative scale invariant heterotic sigma models with a compact target space $M^D$ are conformally invariant. The proof, presented in detail for up to and including two loops, utilises a geometric analogue of the $c$-theorem based on a generalisation of the Perelman's results on geometric flows. Then, we present examples of scale invariant heterotic sigma models with target spaces that exhibit special geometry, which is characterised by the holonomy of the connection with torsion a 3-form, and explore the additional conditions that are necessary for such sigma models to be conformally invariant. For this, we find that the geometry of the target spaces is further restricted to be either conformally balanced or the a priori holonomy of the connection with torsion reduces. We identify the pattern of holonomy reduction in the cases that the holonomy is $SU(n)$ $(D=2n)$, $Sp(k)$ $D=4k)$, $G_2$ $(D=7)$ and $\mathrm{Spin}(7)$ $(D=8)$. We also investigate the properties of these geometries and present some examples., Comment: 35 pages

Synthetic images disseminated online significantly differ from those used during the training and evaluation of the state-of-the-art detectors. In this work, we analyze the performance of synthetic image detectors as deceptive synthetic images evolve throughout their online lifespan. Our study reveals that, despite advancements in the field, current state-of-the-art detectors struggle to distinguish between synthetic and real images in the wild. Moreover, we show that the time elapsed since the initial online appearance of a synthetic image negatively affects the performance of most detectors. Ultimately, by employing a retrieval-assisted detection approach, we demonstrate the feasibility to maintain initial detection performance throughout the whole online lifespan of an image and enhance the average detection efficacy across several state-of-the-art detectors by 6.7% and 7.8% for balanced accuracy and AUC metrics, respectively.

Computer vision (CV) datasets often exhibit biases that are perpetuated by deep learning models. While recent efforts aim to mitigate these biases and foster fair representations, they fail in complex real-world scenarios. In particular, existing methods excel in controlled experiments involving benchmarks with single-attribute injected biases, but struggle with multi-attribute biases being present in well-established CV datasets. Here, we introduce BAdd, a simple yet effective method that allows for learning fair representations invariant to the attributes introducing bias by incorporating features representing these attributes into the backbone. BAdd is evaluated on seven benchmarks and exhibits competitive performance, surpassing state-of-the-art methods on both single- and multi-attribute benchmarks. Notably, BAdd achieves +27.5% and +5.5% absolute accuracy improvements on the challenging multi-attribute benchmarks, FB-Biased-MNIST and CelebA, respectively.

Incomplete Hippocampal Inversion (IHI), sometimes called hippocampal malrotation, is an atypical anatomical pattern of the hippocampus found in about 20% of the general population. IHI can be visually assessed on coronal slices of T1 weighted MR images, using a composite score that combines four anatomical criteria. IHI has been associated with several brain disorders (epilepsy, schizophrenia). However, these studies were based on small samples. Furthermore, the factors (genetic or environmental) that contribute to the genesis of IHI are largely unknown. Large-scale studies are thus needed to further understand IHI and their potential relationships to neurological and psychiatric disorders. However, visual evaluation is long and tedious, justifying the need for an automatic method. In this paper, we propose, for the first time, to automatically rate IHI. We proceed by predicting four anatomical criteria, which are then summed up to form the IHI score, providing the advantage of an interpretable score. We provided an extensive experimental investigation of different machine learning methods and training strategies. We performed automatic rating using a variety of deep learning models (conv5-FC3, ResNet and SECNN) as well as a ridge regression. We studied the generalization of our models using different cohorts and performed multi-cohort learning. We relied on a large population of 2,008 participants from the IMAGEN study, 993 and 403 participants from the QTIM/QTAB studies as well as 985 subjects from the UKBiobank. We showed that deep learning models outperformed a ridge regression. We demonstrated that the performances of the conv5-FC3 network were at least as good as more complex networks while maintaining a low complexity and computation time. We showed that training on a single cohort may lack in variability while training on several cohorts improves generalization., Comment: Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://melba-journal.org/2024:016

Physics-Informed Neural Networks (PINNs) have emerged as a robust framework for solving Partial Differential Equations (PDEs) by approximating their solutions via neural networks and imposing physics-based constraints on the loss function. Traditionally, Multilayer Perceptrons (MLPs) are the neural network of choice, and significant progress has been made in optimizing their training. Recently, Kolmogorov-Arnold Networks (KANs) were introduced as a viable alternative, with the potential of offering better interpretability and efficiency while requiring fewer parameters. In this paper, we present a fast JAX-based implementation of grid-dependent Physics-Informed Kolmogorov-Arnold Networks (PIKANs) for solving PDEs. We propose an adaptive training scheme for PIKANs, incorporating known MLP-based PINN techniques, introducing an adaptive state transition scheme to avoid loss function peaks between grid updates, and proposing a methodology for designing PIKANs with alternative basis functions. Through comparative experiments we demonstrate that these adaptive features significantly enhance training efficiency and solution accuracy. Our results illustrate the effectiveness of PIKANs in improving performance for PDE solutions, highlighting their potential as a superior alternative in scientific and engineering applications.

Generative AI technologies produce hyper-realistic imagery that can be used for nefarious purposes such as producing misleading or harmful content, among others. This makes Synthetic Image Detection (SID) an essential tool for defending against AI-generated harmful content. Current SID methods typically resize input images to a fixed resolution or perform center-cropping due to computational concerns, leading to challenges in effectively detecting artifacts in high-resolution images. To this end, we propose TextureCrop, a novel image pre-processing technique. By focusing on high-frequency image parts where generation artifacts are prevalent, TextureCrop effectively enhances SID accuracy while maintaining manageable memory requirements. Experimental results demonstrate a consistent improvement in AUC across various detectors by 5.7% compared to center cropping and by 14% compared to resizing, across high-resolution images from the Forensynths and Synthbuster datasets., Comment: 17 pages, 6 images

In the field of modern robotics, robots are proving to be useful in tackling high-risk situations, such as navigating hazardous environments like burning buildings, earthquake-stricken areas, or patrolling crime-ridden streets, as well as exploring uncharted caves. These scenarios share similarities with maze exploration problems in terms of complexity. While several methods have been proposed for single-agent systems, ranging from potential fields to flood-fill methods, recent research endeavors have focused on creating methods tailored for multiple agents to enhance the quality and efficiency of maze coverage. The contribution of this paper is the implementation of established maze exploration methods and their comparison with a new cost-utility algorithm designed for multiple agents, which combines the existing methodologies to optimize exploration outcomes. Through a comprehensive and comparative analysis, this paper evaluates the performance of the new approach against the implemented baseline methods from the literature, highlighting its efficacy and potential advantages in various scenarios. The code and experimental results supporting this study are available in the following repository (https://github.com/manouslinard/multiagent-exploration/)., Comment: 12 pages, 15 figures, Conference on Artificial Intelligence SETN 2024. arXiv admin note: text overlap with arXiv:2405.20232

Digital image manipulation has become increasingly accessible and realistic with the advent of generative AI technologies. Recent developments allow for text-guided inpainting, making sophisticated image edits possible with minimal effort. This poses new challenges for digital media forensics. For example, diffusion model-based approaches could either splice the inpainted region into the original image, or regenerate the entire image. In the latter case, traditional image forgery localization (IFL) methods typically fail. This paper introduces the Text-Guided Inpainting Forgery (TGIF) dataset, a comprehensive collection of images designed to support the training and evaluation of image forgery localization and synthetic image detection (SID) methods. The TGIF dataset includes approximately 80k forged images, originating from popular open-source and commercial methods; SD2, SDXL, and Adobe Firefly. Using this data, we benchmark several state-of-the-art IFL and SID methods. Whereas traditional IFL methods can detect spliced images, they fail to detect regenerated inpainted images. Moreover, traditional SID may detect the regenerated inpainted images to be fake, but cannot localize the inpainted area. Finally, both types of methods fail when exposed to stronger compression, while they are less robust to modern compression algorithms, such as WEBP. As such, this work demonstrates the inefficiency of state-of-the-art detectors on local manipulations performed by modern generative approaches, and aspires to help with the development of more capable IFL and SID methods. The dataset can be downloaded at https://github.com/IDLabMedia/tgif-dataset., Comment: 6 pages, submitted to conference

Our collective attention span is shortened by the flood of online information. With \textit{FarFetched}, we address the need for automated claim validation based on the aggregated evidence derived from multiple online news sources. We introduce an entity-centric reasoning framework in which latent connections between events, actions, or statements are revealed via entity mentions and represented in a graph database. Using entity linking and semantic similarity, we offer a way for collecting and combining information from diverse sources in order to generate evidence relevant to the user's claim. Then, we leverage textual entailment recognition to quantitatively determine whether this assertion is credible, based on the created evidence. Our approach tries to fill the gap in automated claim validation for less-resourced languages and is showcased on the Greek language, complemented by the training of relevant semantic textual similarity (STS) and natural language inference (NLI) models that are evaluated on translated versions of common benchmarks., Comment: DeepLo NAACL 2022

Broad Line Regions (BLRs) are known to contain gravitationally-bound gas within r~(few) 10^2-10^3 Schwarszchild radii (Rs) near supermassive black holes (SMBHs) in Active Galactic Nuclei (AGNs). Photo-ionized by strong non-stellar AGN continuum, this gas emits luminous ultraviolet/optical/near-infrared lines from ionized hydrogen (and other multi-ionized atoms) that have the widest velocity profiles observed in galaxies, uniquely indicating the deep gravitational wells of SMBHs. Nearly all BLR studies focus on its ionized gas phase (hereafter BLR+), with typical masses of only a few 10-100 M_Sun, despite strong indications of neutral BLR gas reservoirs (hereafter BLR0) with M_BLR0~10^{5-6} M_Sun. We used the photoionization code CLOUDY, with its chemistry augmented using three-body reactions, to explore 1-D models of dustless BLRs, focusing on the BLR0 conditions, and the abundances of its most prevalent neutral atoms and molecules. A neutral-atom-) and molecule-rich BLR0 gas phase is found underlying the BLR+, the latter occupying only a thin outer layer of AGN-irradiated gas column densities, while the former contains the bulk of the BLR gas mass. Atomic carbon and oxygen as well as the CO molecule can reach substantial abundances in the BLR0, while their lines at infrared and submillimeter wavelengths can yield new probes of the BLR physical conditions and dynamics, unhindered by the dust absorption from outer AGN tori that readily absorb the BLR+ optical/far-ultraviolet (FUV) lines. We find that neutral-atom-rich neutral-atom-rich and even molecule-rich gas can exist in the BLR0. The corresponding spectral lines from neutral atoms and molecules promise a new spectral window of gas dynamics in the vicinity of~SMBHs unhindered by dust absorption. This may even offer the prospect of conducting novel tests of general relativity in strongly curved spacetimes., Comment: Accepted for publication in A&A Letter after language correction

Image data augmentation constitutes a critical methodology in modern computer vision tasks, since it can facilitate towards enhancing the diversity and quality of training datasets; thereby, improving the performance and robustness of machine learning models in downstream tasks. In parallel, augmentation approaches can also be used for editing/modifying a given image in a context- and semantics-aware way. Diffusion Models (DMs), which comprise one of the most recent and highly promising classes of methods in the field of generative Artificial Intelligence (AI), have emerged as a powerful tool for image data augmentation, capable of generating realistic and diverse images by learning the underlying data distribution. The current study realizes a systematic, comprehensive and in-depth review of DM-based approaches for image augmentation, covering a wide range of strategies, tasks and applications. In particular, a comprehensive analysis of the fundamental principles, model architectures and training strategies of DMs is initially performed. Subsequently, a taxonomy of the relevant image augmentation methods is introduced, focusing on techniques regarding semantic manipulation, personalization and adaptation, and application-specific augmentation tasks. Then, performance assessment methodologies and respective evaluation metrics are analyzed. Finally, current challenges and future research directions in the field are discussed., Comment: 53 pages, 15 figures

Automated fact-checking (AFC) is garnering increasing attention by researchers aiming to help fact-checkers combat the increasing spread of misinformation online. While many existing AFC methods incorporate external information from the Web to help examine the veracity of claims, they often overlook the importance of verifying the source and quality of collected "evidence". One overlooked challenge involves the reliance on "leaked evidence", information gathered directly from fact-checking websites and used to train AFC systems, resulting in an unrealistic setting for early misinformation detection. Similarly, the inclusion of information from unreliable sources can undermine the effectiveness of AFC systems. To address these challenges, we present a comprehensive approach to evidence verification and filtering. We create the "CREDible, Unreliable or LEaked" (CREDULE) dataset, which consists of 91,632 articles classified as Credible, Unreliable and Fact checked (Leaked). Additionally, we introduce the EVidence VERification Network (EVVER-Net), trained on CREDULE to detect leaked and unreliable evidence in both short and long texts. EVVER-Net can be used to filter evidence collected from the Web, thus enhancing the robustness of end-to-end AFC systems. We experiment with various language models and show that EVVER-Net can demonstrate impressive performance of up to 91.5% and 94.4% accuracy, while leveraging domain credibility scores along with short or long texts, respectively. Finally, we assess the evidence provided by widely-used fact-checking datasets including LIAR-PLUS, MOCHEG, FACTIFY, NewsCLIPpings+ and VERITE, some of which exhibit concerning rates of leaked and unreliable evidence.

Artificial intelligence systems often address fairness concerns by evaluating and mitigating measures of group discrimination, for example that indicate biases against certain genders or races. However, what constitutes group fairness depends on who is asked and the social context, whereas definitions are often relaxed to accept small deviations from the statistical constraints they set out to impose. Here we decouple definitions of group fairness both from the context and from relaxation-related uncertainty by expressing them in the axiomatic system of Basic fuzzy Logic (BL) with loosely understood predicates, like encountering group members. We then evaluate the definitions in subclasses of BL, such as Product or Lukasiewicz logics. Evaluation produces continuous instead of binary truth values by choosing the logic subclass and truth values for predicates that reflect uncertain context-specific beliefs, such as stakeholder opinions gathered through questionnaires. Internally, it follows logic-specific rules to compute the truth values of definitions. We show that commonly held propositions standardize the resulting mathematical formulas and we transcribe logic and truth value choices to layperson terms, so that anyone can answer them. We also use our framework to study several literature definitions of algorithmic fairness, for which we rationalize previous expedient practices that are non-probabilistic and show how to re-interpret their formulas and parameters in new contexts., Comment: preprint, 32 pages, 7 figures, 2 theorems, 6 appendices

This paper discusses four facets of the Knowledge Distillation (KD) process for Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) architectures, particularly when executed on edge devices with constrained processing capabilities. First, we conduct a comparative analysis of the KD process between CNNs and ViT architectures, aiming to elucidate the feasibility and efficacy of employing different architectural configurations for the teacher and student, while assessing their performance and efficiency. Second, we explore the impact of varying the size of the student model on accuracy and inference speed, while maintaining a constant KD duration. Third, we examine the effects of employing higher resolution images on the accuracy, memory footprint and computational workload. Last, we examine the performance improvements obtained by fine-tuning the student model after KD to specific downstream tasks. Through empirical evaluations and analyses, this research provides AI practitioners with insights into optimal strategies for maximizing the effectiveness of the KD process on edge devices.

The RISC-V SVNAPOT Extension aims to remedy the performance overhead of the Memory Management Unit (MMU), under heavy memory loads. The Privileged Specification defines additional Natural-Power-of-Two (NAPOT) multiples of the 4KB base page size, with 64KB as the default candidate. In this paper we extend the MMU of the Rocket Chip Generator, in order to manage the collocation of 64KB pages along with 4KB pages in the L2 TLB. We present the design challenges we had to overcome and the trade-offs of our design choices. We conduct a preliminary sensitivity analysis of the L2 TLB with different configurations/page sizes. Finally, we summarize on techniques which could further improve memory management performance on RISC-V systems., Comment: Extended abstract accepted to the RISC-V EU Summit 2024 - June 24-28 Munich, Germany

This study builds upon our previous work by introducing a refined Inductive Conformal Martingale (ICM) approach for addressing Concept Drift (CD). Specifically, we enhance our previously proposed CAUTIOUS betting function to incorporate multiple density estimators for improving detection ability. We also combine this betting function with two base estimators that have not been previously utilized within the ICM framework: the Interpolated Histogram and Nearest Neighbor Density Estimators. We assess these extensions using both a single ICM and an ensemble of ICMs. For the latter, we conduct a comprehensive experimental investigation into the influence of the ensemble size on prediction accuracy and the number of available predictions. Our experimental results on four benchmark datasets demonstrate that the proposed approach surpasses our previous methodology in terms of performance while matching or in many cases exceeding that of three contemporary state-of-the-art techniques.

Modern technologies have led illicit firearms trafficking to partially merge with cybercrime, while simultaneously permitting its off-line aspects to become more sophisticated. Law enforcement officers face difficult challenges that require hi-tech solutions. This article presents a real-world system, powered by advanced Artificial Intelligence, for facilitating them in their everyday work.

Although repeatability and reproducibility are essential in science, failed attempts to replicate results across diverse fields made some scientists argue for a reproducibility crisis. In response, several high-profile venues within computing established artifact evaluation tracks, a systematic procedure for evaluating and badging research artifacts, with an increasing number of artifacts submitted. This study compiles recent artifact evaluation procedures and guidelines to show how artifact evaluation in distributed systems research lags behind other computing disciplines and/or is less unified and more complex. We further argue that current artifact assessment criteria are uncoordinated and insufficient for the unique challenges of distributed systems research. We examine the current state of the practice for artifacts and their evaluation to provide recommendations to assist artifact authors, reviewers, and track chairs. We summarize the recommendations and best practices as checklists for artifact authors and evaluation committees. Although our recommendations alone will not resolve the repeatability and reproducibility crisis, we want to start a discussion in our community to increase the number of submitted artifacts and their quality over time., Comment: 13 pages, 2 figures, 3 tables

Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for training pose challenges in ensuring the responsible development of these models, and mitigation through hard prompting or embedding alteration, are the most common present solutions. Our work introduces a novel approach to achieve diverse and inclusive synthetic images by learning a direction in the latent space and solely modifying the initial Gaussian noise provided for the diffusion process. Maintaining a neutral prompt and untouched embeddings, this approach successfully adapts to diverse debiasing scenarios, such as geographical biases. Moreover, our work proves it is possible to linearly combine these learned latent directions to introduce new mitigations, and if desired, integrate it with text embedding adjustments. Furthermore, text-to-image models lack transparency for assessing bias in outputs, unless visually inspected. Thus, we provide a tool to empower developers to select their desired concepts to mitigate. The project page with code is available online., Comment: Accepted at CVPR workshop 2024, proceedings of ReGenAI: First Workshop on Responsible Generative AI

This is a point of view of the work of Herbert Busemann (1905-1994), seen as a return to the geometry of Ancient Greece. The importance of this work, its recognition and its relation with other works are discussed. The final version of this paper will appear in the Handbook of the History and Philosophy of Mathematical Practice, ed. Bharath Sriraman, Springer, 2024.

Robotic exploration has long captivated researchers aiming to map complex environments efficiently. Techniques such as potential fields and frontier exploration have traditionally been employed in this pursuit, primarily focusing on solitary agents. Recent advancements have shifted towards optimizing exploration efficiency through multiagent systems. However, many existing approaches overlook critical real-world factors, such as broadcast range limitations, communication costs, and coverage overlap. This paper addresses these gaps by proposing a distributed maze exploration strategy (CU-LVP) that assumes constrained broadcast ranges and utilizes Voronoi diagrams for better area partitioning. By adapting traditional multiagent methods to distributed environments with limited broadcast ranges, this study evaluates their performance across diverse maze topologies, demonstrating the efficacy and practical applicability of the proposed method. The code and experimental results supporting this study are available in the following repository: https://github.com/manouslinard/multiagent-exploration/., Comment: 11 pages, 9 figures

Creating fair AI systems is a complex problem that involves the assessment of context-dependent bias concerns. Existing research and programming libraries express specific concerns as measures of bias that they aim to constrain or mitigate. In practice, one should explore a wide variety of (sometimes incompatible) measures before deciding which ones warrant corrective action, but their narrow scope means that most new situations can only be examined after devising new measures. In this work, we present a mathematical framework that distils literature measures of bias into building blocks, hereby facilitating new combinations to cover a wide range of fairness concerns, such as classification or recommendation differences across multiple multi-value sensitive attributes (e.g., many genders and races, and their intersections). We show how this framework generalizes existing concepts and present frequently used blocks. We provide an open-source implementation of our framework as a Python library, called FairBench, that facilitates systematic and extensible exploration of potential bias concerns., Comment: Workshop on AI bias: Measurements, Mitigation, Explanation Strategies (AIMMES 2024)

Advanced control, operation, and planning tools of electrical networks with ML are not straightforward. 110 experts were surveyed to show where and how ML algorithms could advance. This paper assesses this survey and research environment. Then, it develops an innovation roadmap that helps align our research community with a goal-oriented realisation of the opportunities that AI upholds. This paper finds that the R&D environment of system operators (and the surrounding research ecosystem) needs adaptation to enable faster developments with AI while maintaining high testing quality and safety. This roadmap serves system operators, academics, and labs advancing next-generation electrical network tools., Comment: 5 pages, to be presented IEEE PES Innovative Smart Grid Technologies Europe 2024

The abundance of information present in Whole Slide Images (WSIs) makes them useful for prognostic evaluation. A large number of models utilizing a pretrained ResNet backbone have been released and employ various feature aggregation techniques, primarily based on Multiple Instance Learning (MIL). By leveraging the recently released UNI feature extractor, existing models can be adapted to achieve higher accuracy, which paves the way for more robust prognostic tools in digital pathology., Comment: 4 pages, preliminary results exploring UNI feature extractor, will attempt to gather more results and check again for correctness and consistency

Federated learning (FL) is a decentralized learning technique that enables participating devices to collaboratively build a shared Machine Leaning (ML) or Deep Learning (DL) model without revealing their raw data to a third party. Due to its privacy-preserving nature, FL has sparked widespread attention for building Intrusion Detection Systems (IDS) within the realm of cybersecurity. However, the data heterogeneity across participating domains and entities presents significant challenges for the reliable implementation of an FL-based IDS. In this paper, we propose an effective method called Statistical Averaging (StatAvg) to alleviate non-independently and identically (non-iid) distributed features across local clients' data in FL. In particular, StatAvg allows the FL clients to share their individual data statistics with the server, which then aggregates this information to produce global statistics. The latter are shared with the clients and used for universal data normalisation. It is worth mentioning that StatAvg can seamlessly integrate with any FL aggregation strategy, as it occurs before the actual FL training process. The proposed method is evaluated against baseline approaches using datasets for network and host Artificial Intelligence (AI)-powered IDS. The experimental results demonstrate the efficiency of StatAvg in mitigating non-iid feature distributions across the FL clients compared to the baseline methods., Comment: 10 pages, 8 figures

Synthetically generated images can be used to create media content or to complement datasets for training image analysis models. Several methods have recently been proposed for the synthesis of high-fidelity face images; however, the potential biases introduced by such methods have not been sufficiently addressed. This paper examines the bias introduced by the widely popular StyleGAN2 generative model trained on the Flickr Faces HQ dataset and proposes two sampling strategies to balance the representation of selected attributes in the generated face images. We focus on two protected attributes, gender and age, and reveal that biases arise in the distribution of randomly sampled images against very young and very old age groups, as well as against female faces. These biases are also assessed for different image quality levels based on the GIQA score. To mitigate bias, we propose two alternative methods for sampling on selected lines or spheres of the latent space to increase the number of generated samples from the under-represented classes. The experimental results show a decrease in bias against underrepresented groups and a more uniform distribution of the protected features at different levels of image quality., Comment: Accepted to the BIAS 2023 ECML-PKDD Workshop

Light-ring bifurcations that can occur for prolate non-Kerr compact objects can leave an indelible signature on SMBH shadows as a fractal sequence of eyebrow-like formations. These fractal features are the result of two properties of these spacetimes. The first is that they allow for multiple escapes for the photons (throats in the effective potential of photon geodesic motion). The second is that photon geodesics can resonate between different generalized light-rings related to the escapes, called fundamental photon orbits, that lead photons to alternate between the different exits either towards the compact object or infinity. The resulting fractal structures of the shadow seem to be a generic feature of prolate non-Kerr objects that may be observable in (accretion-disk)-illuminated compact objects, especially along equatorial lines of sight, but the best orientation depends on the specific parameters. Such fractal features if observed in the shadows of singular supermassive black holes at the centers of galaxies, would be smoking gun signals of non-Kerr compact objects., Comment: 17 pages, 20 figures. Accepted for publication in Physical Review D

By adapting previously known arguments concerning Ricci flow and the c-theorem, we give a direct proof that in a two-dimensional sigma-model with compact target space, scale invariance implies conformal invariance in perturbation theory. This argument, which applies to a general sigma-model constructed with a target space metric and B-field, is in accord with a more general proof in the literature that applies to arbitrary two-dimensional quantum field theories. Models with extended supersymmetry and a B-field are known to provide interesting test cases for the relation between scale invariance and conformal invariance in sigma-model perturbation theory. We give examples showing that in such models, the obstructions to conformal invariance suggested by general arguments can actually occur in models with target spaces that are not compact or complete. Thus compactness of the target space, or at least a suitable condition of completeness, is necessary as well as sufficient to ensure that scale invariance implies conformal invariance in models of this type., Comment: 31 pp, minor corrections, references added

This is the first paper to systematically study the earthquake metric, an asymmetric Finsler metric on Teichm{\"u}ller space introduced by Thurston. We provide proofs for several assertions of Thurston and establish new properties of this metric, among which are incompleteness, asymptotic distance to the boundary and comparisons with the Thurston metric and the Weil--Petersson metric. In doing so, we propose a novel asymmetric generalisation of the notion of completion for symmetric metrics, which we call the FD-completion, and prove that for the earthquake metric the FD-completion and various symmetrised metric completions coincide with the Weil--Petersson completion. We also answer a question of Thurston by giving an interpretation of this metric arising from a global minimisation problem, namely, the earthquake magnitude minimisation problem. At several points of this paper, we formulate a certain number of open problems which will show that the earthquake metric constitutes a promising subject.

In this paper we propose a new framework for evaluating the performance of explanation methods on the decisions of a deepfake detector. This framework assesses the ability of an explanation method to spot the regions of a fake image with the biggest influence on the decision of the deepfake detector, by examining the extent to which these regions can be modified through a set of adversarial attacks, in order to flip the detector's prediction or reduce its initial prediction; we anticipate a larger drop in deepfake detection accuracy and prediction, for methods that spot these regions more accurately. Based on this framework, we conduct a comparative study using a state-of-the-art model for deepfake detection that has been trained on the FaceForensics++ dataset, and five explanation methods from the literature. The findings of our quantitative and qualitative evaluations document the advanced performance of the LIME explanation method against the other compared ones, and indicate this method as the most appropriate for explaining the decisions of the utilized deepfake detector., Comment: Accepted for publication, 3rd ACM Int. Workshop on Multimedia AI against Disinformation (MAD'24) at ACM ICMR'24, June 10, 2024, Phuket, Thailand. This is the "accepted version"

The generative AI technology offers an increasing variety of tools for generating entirely synthetic images that are increasingly indistinguishable from real ones. Unlike methods that alter portions of an image, the creation of completely synthetic images presents a unique challenge and several Synthetic Image Detection (SID) methods have recently appeared to tackle it. Yet, there is often a large gap between experimental results on benchmark datasets and the performance of methods in the wild. To better address the evaluation needs of SID and help close this gap, this paper introduces a benchmarking framework that integrates several state-of-the-art SID models. Our selection of integrated models was based on the utilization of varied input features, and different network architectures, aiming to encompass a broad spectrum of techniques. The framework leverages recent datasets with a diverse set of generative models, high level of photo-realism and resolution, reflecting the rapid improvements in image synthesis technology. Additionally, the framework enables the study of how image transformations, common in assets shared online, such as JPEG compression, affect detection performance. SIDBench is available on https://github.com/mever-team/sidbench and is designed in a modular manner to enable easy inclusion of new datasets and SID models.

AI systems rely on extensive training on large datasets to address various tasks. However, image-based systems, particularly those used for demographic attribute prediction, face significant challenges. Many current face image datasets primarily focus on demographic factors such as age, gender, and skin tone, overlooking other crucial facial attributes like hairstyle and accessories. This narrow focus limits the diversity of the data and consequently the robustness of AI systems trained on them. This work aims to address this limitation by proposing a methodology for generating synthetic face image datasets that capture a broader spectrum of facial diversity. Specifically, our approach integrates a systematic prompt formulation strategy, encompassing not only demographics and biometrics but also non-permanent traits like make-up, hairstyle, and accessories. These prompts guide a state-of-the-art text-to-image model in generating a comprehensive dataset of high-quality realistic images and can be used as an evaluation set in face analysis systems. Compared to existing datasets, our proposed dataset proves equally or more challenging in image classification tasks while being much smaller in size.

Self-Supervised Learning (SSL) is a valuable and robust training methodology for contemporary Deep Neural Networks (DNNs), enabling unsupervised pretraining on a `pretext task' that does not require ground-truth labels/annotation. This allows efficient representation learning from massive amounts of unlabeled training data, which in turn leads to increased accuracy in a `downstream task' by exploiting supervised transfer learning. Despite the relatively straightforward conceptualization and applicability of SSL, it is not always feasible to collect and/or to utilize very large pretraining datasets, especially when it comes to real-world application settings. In particular, in cases of specialized and domain-specific application scenarios, it may not be achievable or practical to assemble a relevant image pretraining dataset in the order of millions of instances or it could be computationally infeasible to pretrain at this scale. This motivates an investigation on the effectiveness of common SSL pretext tasks, when the pretraining dataset is of relatively limited/constrained size. In this context, this work introduces a taxonomy of modern visual SSL methods, accompanied by detailed explanations and insights regarding the main categories of approaches, and, subsequently, conducts a thorough comparative experimental evaluation in the low-data regime, targeting to identify: a) what is learnt via low-data SSL pretraining, and b) how do different SSL categories behave in such training scenarios. Interestingly, for domain-specific downstream tasks, in-domain low-data SSL pretraining outperforms the common approach of large-scale pretraining on general datasets. Grounded on the obtained results, valuable insights are highlighted regarding the performance of each category of SSL methods, which in turn suggest straightforward future research directions in the field.

The developing field of enhanced diagnostic techniques in the diagnosis of infectious diseases, constitutes a crucial domain in modern healthcare. By utilizing Gas Chromatography-Ion Mobility Spectrometry (GC-IMS) data and incorporating machine learning algorithms into one platform, our research aims to tackle the ongoing issue of precise infection identification. Inspired by these difficulties, our goals consist of creating a strong data analytics process, enhancing machine learning (ML) models, and performing thorough validation for clinical applications. Our research contributes to the emerging field of advanced diagnostic technologies by integrating Gas Chromatography-Ion Mobility Spectrometry (GC-IMS) data and machine learning algorithms within a unified Laboratory Information Management System (LIMS) platform. Preliminary trials demonstrate encouraging levels of accuracy when employing various ML algorithms to differentiate between infected and non-infected samples. Continuing endeavors are currently concentrated on enhancing the effectiveness of the model, investigating techniques to clarify its functioning, and incorporating many types of data to further support the early detection of diseases., Comment: EEITE 2024, IEEE Conference

Biometric Verification (BV) systems often exhibit accuracy disparities across different demographic groups, leading to biases in BV applications. Assessing and quantifying these biases is essential for ensuring the fairness of BV systems. However, existing bias evaluation metrics in BV have limitations, such as focusing exclusively on match or non-match error rates, overlooking bias on demographic groups with performance levels falling between the best and worst performance levels, and neglecting the magnitude of the bias present. This paper presents an in-depth analysis of the limitations of current bias evaluation metrics in BV and, through experimental analysis, demonstrates their contextual suitability, merits, and limitations. Additionally, it introduces a novel general-purpose bias evaluation measure for BV, the ``Sum of Group Error Differences (SEDG)''. Our experimental results on controlled synthetic datasets demonstrate the effectiveness of demographic bias quantification when using existing metrics and our own proposed measure. We discuss the applicability of the bias evaluation metrics in a set of simulated demographic bias scenarios and provide scenario-based metric recommendations. Our code is publicly available under \url{https://github.com/alaaobeid/SEDG}.

Quantum key distribution (QKD) and quantum message encryption protocols promise a secure way to distribute information while detecting eavesdropping. However, current protocols may suffer from significantly reduced eavesdropping protection when only a subset of qubits are observed by an attacker. In this paper, we present two quantum cryptographic protocols leveraging the quantum Fourier transform (QFT) and show their higher effectiveness even when an attacker measures only a subset of the transmitted qubits. The foremost of these protocols is a novel QKD method that leverages this effectiveness of the QFT while being more practical than previously proposed QFT-based protocols, most notably by not relying on quantum memory. We additionally show how existing quantum encryption methods can be augmented with a QFT-based approach to improve eavesdropping detection. Finally, we provide equations to analyze different QFT-based detection schemes within these protocols so that protocol designers can make custom schemes for their purpose., Comment: 9 pages, 5 figures, 1 table, submitted to 2024 IEEE International Conference on Quantum Computing & Engineering (QCE24)

Compact laser-plasma acceleration of fast ions has made great strides since its discovery over two decades ago, resulting in the current generation of high-energy ($\geq 100\,\rm MeV$) ultracold beams over ultrashort ($\leq 1\,\rm ps$) durations. To unlock broader applications of these beams, we need the ability to tailor the ion energy spectrum. Here, we present a scheme that achieves precisely this by accelerating protons in a "lighthouse" fashion, whereby the highest-energy component of the beam is emitted in a narrow cone, well separated from the lower-energy components. This is made possible by a two-stage interaction in which the rear surface of the target is first set into rapid motion before the main acceleration phase. This approach offers the additional advantages of leveraging a robust sheath acceleration process in standard micron-thick targets and being optically controllable., Comment: 9 pages, 6 figures

As the global population ages, the number of fall-related incidents is on the rise. Effective fall detection systems, specifically in healthcare sector, are crucial to mitigate the risks associated with such events. This study evaluates the role of visual context, including background objects, on the accuracy of fall detection classifiers. We present a segmentation pipeline to semi-automatically separate individuals and objects in images. Well-established models like ResNet-18, EfficientNetV2-S, and Swin-Small are trained and evaluated. During training, pixel-based transformations are applied to segmented objects, and the models are then evaluated on raw images without segmentation. Our findings highlight the significant influence of visual context on fall detection. The application of Gaussian blur to the image background notably improves the performance and generalization capabilities of all models. Background objects such as beds, chairs, or wheelchairs can challenge fall detection systems, leading to false positive alarms. However, we demonstrate that object-specific contextual transformations during training effectively mitigate this challenge. Further analysis using saliency maps supports our observation that visual context is crucial in classification tasks. We create both dataset processing API and segmentation pipeline, available at https://github.com/A-NGJ/image-segmentation-cli., Comment: 10 pages, 6 figures, KES IDT-24 conference

In-band network telemetry (INT), empowered by programmable dataplanes such as P4, comprises a viable approach to network monitoring and telemetry analysis. However, P4-INT as well as other existing frameworks for INT yield a substantial transmission overhead, which grows linearly with the number of hops and the number of telemetry values. To address this issue, we present a deterministic and a probabilistic technique for lightweight INT, termed as DLINT and PLINT,respectively. In particular, DLINT exercises per-flow aggregation by spreading the telemetry values across the packets of a flow. DLINT relies on switch coordination through the use of per-flow telemetry states, maintained within P4 switches. Furthermore, DLINT utilizes Bloom Filters (BF) in order to compress the state lookup tables within P4 switches. On the other hand, PLINT employs a probabilistic approach based on reservoir sampling. PLINT essentially empowers every INT node to insert telemetry values with equal probability within each packet. Our evaluation results corroborate that both proposed techniques alleviate the transmission overhead of P4-INT, while maintaining a high degree of monitoring accuracy. In addition, we perform a comparative evaluation between DLINT and PLINT. DLINT is more effective in conveying path traces to the telemetry server, whereas PLINT detects more promptly path updates exploiting its more efficient INT header space utilization

Sub-terahertz (subTHz) antennas will play an important role in the next generations of wireless communication systems. However, when comes to the subTHz frequency spectrum, the antenna fabrication tolerance needs to be accurately considered during the design stage. The classic approach to studying the average performance of an antenna design considering fabrication tolerances is through the use of the Monte-Carlo (MC) method. In this paper, we propose an adaptive polynomial chaos expansion (PCE) method for the uncertainty quantification analysis of subTHz horn antennas with flat-top radiation patterns. The proposed method builds a surrogate model of the antenna's response to electromagnetic (EM) excitation and estimates its statistical moments with accuracy close to the reference MC method, but with a much smaller computational complexity of roughly two orders of magnitude. Moreover, the surrogate model based on PCE can substitute full-wave EM solvers in producing samples for electromagnetic quantities of interest, resulting in significant computational efficiency gains during optimization tasks. To this end, we successfully combined PCE with the particle swarm optimization method to design the free parameters of a horn antenna at $95$ GHz for a flat-top gain., Comment: 10 pages, 12 figures, submitted to an IEEE Transactions Journal

Performance during perceptual decision-making exhibits an inverted-U relationship with arousal, but the underlying network mechanisms remain unclear. Here, we recorded from auditory cortex (A1) of behaving mice during passive tone presentation, while tracking arousal via pupillometry. We found that tone discriminability in A1 ensembles was optimal at intermediate arousal, revealing a population-level neural correlate of the inverted-U relationship. We explained this arousal-dependent coding using a spiking network model with a clustered architecture. Specifically, we show that optimal stimulus discriminability is achieved near a transition between a multi-attractor phase with metastable cluster dynamics (low arousal) and a single-attractor phase (high arousal). Additional signatures of this transition include arousal-induced reductions of overall neural variability and the extent of stimulus-induced variability quenching, which we observed in the empirical data. Our results elucidate computational principles underlying interactions between pupil-linked arousal, sensory processing, and neural variability, and suggest a role for phase transitions in explaining nonlinear modulations of cortical computations.

The problem of constructing optimal factoring automata arises in the context of unification factoring for the efficient execution of logic programs. Given an ordered set of $n$ strings of length $m$, the problem is to construct a trie-like tree structure of minimum size in which the leaves in left-to-right order represent the input strings in the given order. Contrary to standard tries, the order in which the characters of a string are encountered can be different on different root-to-leaf paths. Dawson et al. [ACM Trans. Program. Lang. Syst. 18(5):528--563, 1996] gave an algorithm that solves the problem in time $O(n^2 m (n+m))$. In this paper, we present an improved algorithm with running-time $O(n^2m)$.

Mekler's construction is a powerful technique for building purely algebraic structures from combinatorial ones. Its power lies in the fact that it allows various model-theoretic tameness properties of the combinatorial structure to transfer to the algebraic one. In this paper, we push this ideology much further, describing a broad class of properties that transfer through Mekler's construction. This technique subsumes many well-known results and opens avenues for many more. As a straightforward application of our methods, we (1) obtain transfer principles for stably embedded pairs of Mekler groups and (2) construct the first examples of strictly $\mathsf{NFOP}_k$ pure groups for all $k\in\mathbb{N}_{>2}$. We also answer a question of Chernikov and Hempel on the transfer of burden., Comment: 45 pages. Preliminary version, comments welcome!

Illicit object detection is a critical task performed at various high-security locations, including airports, train stations, subways, and ports. The continuous and tedious work of examining thousands of X-ray images per hour can be mentally taxing. Thus, Deep Neural Networks (DNNs) can be used to automate the X-ray image analysis process, improve efficiency and alleviate the security officers' inspection burden. The neural architectures typically utilized in relevant literature are Convolutional Neural Networks (CNNs), with Vision Transformers (ViTs) rarely employed. In order to address this gap, this paper conducts a comprehensive evaluation of relevant ViT architectures on illicit item detection in X-ray images. This study utilizes both Transformer and hybrid backbones, such as SWIN and NextViT, and detectors, such as DINO and RT-DETR. The results demonstrate the remarkable accuracy of the DINO Transformer detector in the low-data regime, the impressive real-time performance of YOLOv8, and the effectiveness of the hybrid NextViT backbone.