arXiv subjects

Thomas Lagkas

Publications and source records attributed to Thomas Lagkas.

15 recordsLinked to original sources

arXiv2026

HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems

Autonomous multi-agent systems nowadays act in finance, software supply chains, and security operations. Already, the first largely AI-orchestrated intrusion campaigns have been reported. Yet, when such a system causes harm, no method can robustly establish what happened, what caused it, or who is accountable. This is because provenance forensics works at the wrong abstraction, formal causality assumes the causal model, and agent auditing trusts self-recording. The target failure mode is, thus, attribution laundering, i.e., spreading an act across redundant agents until none is a but-for cause. Worse, the record is produced by the suspects, which comprises the assumption adopted throughout this work. Agents may therefore anticipate the investigation and the part of logging infrastructure may itself collude. In this paper, HANSARD is proposed, a reference architecture treating accountability as a life-cycle property. First, a readiness profile sealed before operation bounds what later findings may claim. Second, capturing at five choke points beyond the agents' reach makes omissions detectable, not only tampering. Third, a typed PROV-DM-aligned causal graph accrues as the system runs, and three indicators read it live to gate oversight without adjudicating. Fourth, post-incident replay yields contingent effects under the modified Halpern-Pearl definition, together with a compensation-set size. Finally, a synergy residual measures harm due to the combination rather than to individuals, making laundering visible. Cause, responsibility and accountability are then reported separately, each capped by an evidentiary tier, while a future research agenda is also provided.

cs.AI↗

arXiv2026

Facial Affect Analysis for Service-Oriented Systems: Advances, Challenges, and Future Visions

Facial Affect Analysis (FAA) is evolving from a stand-alone recognition task into a reusable perception capability for Service-Oriented Software Ecosystems (SoSE). This paper preserves the FAA methodological core while reframing recent advances through systems-engineering requirements for composable and dependable services. We review representative progress in static and dynamic expression analysis, action-unit and micro-expression modeling, and modern CNN, Transformer, graph, and hybrid architectures, then interpret these advances by their operational fit in edge, cloud, and hybrid service pipelines. The synthesis emphasizes SoSE concerns that determine deployability: service contracts for uncertainty-aware outputs, latency and availability envelopes, lifecycle monitoring and recalibration, governance-aware integration, and interoperability across independently evolving components. Our analysis shows that benchmark gains alone are insufficient for SoSE readiness; robustness under shift, intervention stability, fairness, privacy posture, and runtime guarantees are equally critical. We conclude with a roadmap for treating FAA as an operational service component with explicit interfaces, measurable quality attributes, and accountable lifecycle management.

cs.CV↗

arXiv2026

Facial Expression Recognition in the Deep Learning Era: A Systematic Multi-Criteria Review of Methods, Models, Datasets, Performance, Challenges, and Future Research Directions

Facial Expression Recognition (FER) has advanced rapidly over the last decade, driven by the shift from handcrafted descriptors and shallow classifiers to deep convolutional, attention-based, vision-language, and foundation-model architectures, and by the parallel growth of large-scale in-the-wild benchmarks spanning categorical, dimensional, compound, micro-expression, Action Unit (AU), and intensity-estimation tasks. Yet the deep learning-based FER landscape has so far been reviewed only along narrow task-, architecture-, or application-specific axes, leaving a holistic, systematically organized account of its recent advances missing. This survey addresses that gap with a comprehensive review of recent deep learning-based FER, explicitly linked to the wider Facial Affect Recognition (FAR) domain. Its main contributions are: a) A description of FER's evolution into five distinct phases, from handcrafted features and classical machine learning to attention-based, vision-language, and foundation-model approaches, with the key milestone works of each, b) A multi-criteria taxonomy analyzing the literature along seven complementary axes: recognition task, input modality, face pre-processing pipeline, network architecture, learning strategy, acquisition setting, and application domain, c) A per-criterion comparative analysis, with critical insights into the strengths and limitations of each category under in-the-wild conditions, d) A task-organized review of public FER datasets, with their annotation schemes, modalities, and evaluation protocols, e) A compilation of performance metrics and a per-task quantitative comparison of representative state-of-the-art methods on widely adopted benchmarks, and f) A discussion of current challenges and promising future directions.

cs.CV↗

arXiv2025

Automated Modeling Method for Pathloss Model Discovery

Modeling propagation is the cornerstone for designing and optimizing next-generation wireless systems, with a particular emphasis on 5G and beyond era. Traditional modeling methods have long relied on statistic-based techniques to characterize propagation behavior across different environments. With the expansion of wireless communication systems, there is a growing demand for methods that guarantee the accuracy and interpretability of modeling. Artificial intelligence (AI)-based techniques, in particular, are increasingly being adopted to overcome this challenge, although the interpretability is not assured with most of these methods. Inspired by recent advancements in AI, this paper proposes a novel approach that accelerates the discovery of path loss models while maintaining interpretability. The proposed method automates the formulation, evaluation, and refinement of the model, facilitating the discovery of the model. We examine two techniques: one based on Deep Symbolic Regression, offering full interpretability, and the second based on Kolmogorov-Arnold Networks, providing two levels of interpretability. Both approaches are evaluated on two synthetic and two real-world datasets. Our results show that Kolmogorov-Arnold Networks achieve the coefficient of determination value R^2 close to 1 with minimal prediction error, while Deep Symbolic Regression generates compact models with moderate accuracy. Moreover, on the selected examples, we demonstrate that automated methods outperform traditional methods, achieving up to 75% reduction in prediction errors, offering accurate and explainable solutions with potential to increase the efficiency of discovering next-generation path loss models.

cs.LG↗

arXiv2025

Malware Detection in Docker Containers: An Image is Worth a Thousand Logs

Malware detection is increasingly challenged by evolving techniques like obfuscation and polymorphism, limiting the effectiveness of traditional methods. Meanwhile, the widespread adoption of software containers has introduced new security challenges, including the growing threat of malicious software injection, where a container, once compromised, can serve as entry point for further cyberattacks. In this work, we address these security issues by introducing a method to identify compromised containers through machine learning analysis of their file systems. We cast the entire software containers into large RGB images via their tarball representations, and propose to use established Convolutional Neural Network architectures on a streaming, patch-based manner. To support our experiments, we release the COSOCO dataset--the first of its kind--containing 3364 large-scale RGB images of benign and compromised software containers at https://huggingface.co/datasets/k3ylabs/cosoco-image-dataset. Our method detects more malware and achieves higher F1 and Recall scores than all individual and ensembles of VirusTotal engines, demonstrating its effectiveness and setting a new standard for identifying malware-compromised software containers.

cs.CR↗

arXiv2025

Federated Detection of Open Charge Point Protocol 1.6 Cyberattacks

The ongoing electrification of the transportation sector requires the deployment of multiple Electric Vehicle (EV) charging stations across multiple locations. However, the EV charging stations introduce significant cyber-physical and privacy risks, given the presence of vulnerable communication protocols, like the Open Charge Point Protocol (OCPP). Meanwhile, the Federated Learning (FL) paradigm showcases a novel approach for improved intrusion detection results that utilize multiple sources of Internet of Things data, while respecting the confidentiality of private information. This paper proposes the adoption of the FL architecture for the monitoring of the EV charging infrastructure and the detection of cyberattacks against the OCPP 1.6 protocol. The evaluation results showcase high detection performance of the proposed FL-based solution.

cs.CR↗

arXiv2024

StatAvg: Mitigating Data Heterogeneity in Federated Learning for Intrusion Detection Systems

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.

cs.CR↗

arXiv2023

Evaluation of Environmental Conditions on Object Detection using Oriented Bounding Boxes for AR Applications

The objective of augmented reality (AR) is to add digital content to natural images and videos to create an interactive experience between the user and the environment. Scene analysis and object recognition play a crucial role in AR, as they must be performed quickly and accurately. In this study, a new approach is proposed that involves using oriented bounding boxes with a detection and recognition deep network to improve performance and processing time. The approach is evaluated using two datasets: a real image dataset (DOTA dataset) commonly used for computer vision tasks, and a synthetic dataset that simulates different environmental, lighting, and acquisition conditions. The focus of the evaluation is on small objects, which are difficult to detect and recognise. The results indicate that the proposed approach tends to produce better Average Precision and greater accuracy for small objects in most of the tested conditions.

cs.CV↗

arXiv2023

AI-Powered Interfaces for Extended Reality to support Remote Maintenance

High-end components that conduct complicated tasks automatically are a part of modern industrial systems. However, in order for these parts to function at the desired level, they need to be maintained by qualified experts. Solutions based on Augmented Reality (AR) have been established with the goal of raising production rates and quality while lowering maintenance costs. With the introduction of two unique interaction interfaces based on wearable targets and human face orientation, we are proposing hands-free advanced interactive solutions in this study with the goal of reducing the bias towards certain users. Using traditional devices in real time, a comparison investigation using alternative interaction interfaces is conducted. The suggested solutions are supported by various AI powered methods such as novel gravity-map based motion adjustment that is made possible by predictive deep models that reduce the bias of traditional hand- or finger-based interaction interfaces

cs.HC↗

arXiv2023

Evaluation of AI-Supported Input Methods in Augmented Reality Environment

Augmented Reality (AR) solutions are providing tools that could improve applications in the medical and industrial fields. Augmentation can provide additional information in training, visualization, and work scenarios, to increase efficiency, reliability, and safety, while improving communication with other devices and systems on the network. Unfortunately, tasks in these fields often require both hands to execute, reducing the variety of input methods suitable to control AR applications. People with certain physical disabilities, where they are not able to use their hands, are also negatively impacted when using these devices. The goal of this work is to provide novel hand-free interfacing methods, using AR technology, in association with AI support approaches to produce an improved Human-Computer interaction solution.

cs.HC↗

arXiv2020

Signal strength based scheme for following mobile IoT devices in dynamic environments

The increased maturity level of technological achievements towards the realization of the Internet of Things (IoT) vision allowed sophisticated solutions to emerge, offering reliable monitoring in highly dynamic environments that lack well-defined and well-designed infrastructures. In this paper, we use a bio-inspired IoT architecture, which allows flexible creation and discovery of sensor-based services offering self-organization and self-optimization properties to the dynamic network, in order to make the required monitoring information available. The main contribution of the paper is the introduction of a new algorithm for following mobile monitored targets/individuals in the context of an IoT system, especially a dynamic one as the aforementioned. The devised technique, called Hot-Cold, is able to ensure proximity maintenance by the tracking robotic device solely based on the strength of the RF signal broadcasted by the target to communicate its sensors' data. Complete geometrical, numerical, simulation, and convergence analyses of the proposed technique are thoroughly presented, along with a detailed simulation-based evaluation that reveals the higher following accuracy of Hot-Cold compared to the popular concept of trilateration-based tracking. Finally, a prototype of the full architecture was implemented not only to demonstrate the applicability of the presented approach for monitoring in dynamic environments, but also the operability of the introduced tracking technique.

cs.NI↗

arXiv2019

The evolution of argumentation mining: From models to social media and emerging tools

Argumentation mining is a rising subject in the computational linguistics domain focusing on extracting structured arguments from natural text, often from unstructured or noisy text. The initial approaches on modeling arguments was aiming to identify a flawless argument on specific fields (Law, Scientific Papers) serving specific needs (completeness, effectiveness). With the emerge of Web 2.0 and the explosion in the use of social media both the diffusion of the data and the argument structure have changed. In this survey article, we bridge the gap between theoretical approaches of argumentation mining and pragmatic schemes that satisfy the needs of social media generated data, recognizing the need for adapting more flexible and expandable schemes, capable to adjust to the argumentation conditions that exist in social media. We review, compare, and classify existing approaches, techniques and tools, identifying the positive outcome of combining tasks and features, and eventually propose a conceptual architecture framework. The proposed theoretical framework is an argumentation mining scheme able to identify the distinct sub-tasks and capture the needs of social media text, revealing the need for adopting more flexible and extensible frameworks.

cs.IR↗

arXiv2019

Smart IoT Cameras for Crowd Analysis based on augmentation for automatic pedestrian detection, simulation and annotation

Smart video sensors for applications related to surveillance and security are IOT-based as they use Internet for various purposes. Such applications include crowd behaviour monitoring and advanced decision support systems operating and transmitting information over internet. The analysis of crowd and pedestrian behaviour is an important task for smart IoT cameras and in particular video processing. In order to provide related behavioural models, simulation and tracking approaches have been considered in the literature. In both cases ground truth is essential to train deep models and provide a meaningful quantitative evaluation. We propose a framework for crowd simulation and automatic data generation and annotation that supports multiple cameras and multiple targets. The proposed approach is based on synthetically generated human agents, augmented frames and compositing techniques combined with path finding and planning methods. A number of popular crowd and pedestrian data sets were used to validate the model, and scenarios related to annotation and simulation were considered.

cs.CV↗

arXiv2018

Argumentation Mining: Exploiting Multiple Sources and Background Knowledge

The field of Argumentation Mining has arisen from the need of determining the underlying causes from an expressed opinion and the urgency to develop the established fields of Opinion Mining and Sentiment Analysis. The recent progress in the wider field of Artificial Intelligence in combination with the available data through Social Web has create great potential for every sub-field of Natural Language Process including Argumentation Mining.

cs.IR↗

arXiv2018

Feasibility of sensor-based technology for monitoring health in developing countries - cost analysis and user perception aspects

Understanding the financial burden of chronic diseases in developing regions still remains an important economical factor which influences the successful implementation of sensor based applications for continuous monitoring of chronic conditions. Our research focused on a comparison of literature-based data with real costs of the management and treatment of chronic diseases in a developing country, and we are using Kosovo as an example here. The results reveal that the actual living costs exceed the minimum expenses that chronic diseases impose. Following the potential of a positive economic impact of sensor based platforms for monitoring chronic conditions, we further examined the users perception of digital technology. The purpose of this paper is to present the varying cost levels of treating chronic diseases, identify the users concerns and requirements towards digital technology and discuss issues and challenges that the application of sensor based platforms imply in low and middle income countries.

cs.CY↗