Research Papers

Trustworthy AI requires reliable data-processing pipelines, not only robust downstream predictive models. As an upstream component, data summarization determines which information is retained and passed to subsequent learning or decision modules. Therefore, adversarial perturbations to the summarization process can compromise trustworthy AI in an upstream manner: they may alter the selected summary, reduce its representativeness, and further degrade the utility of subsequent learning tasks. In this paper, we study adversarial attacks on continuous data summarization under similarity-level perturbations through DR-submodular optimization. We show that a class of multi-resolution image summarization objectives can be formulated as multilinear extensions of non-negative submodular set functions and satisfy DR-submodularity with $m$-weak monotonicity. We then formulate multi-target attack generation as a min-max problem, where one admissible perturbation of the similarity structure is optimized to degrade multiple target summarization models. To mitigate such perturbations, we formulate robust defense against mixed attack types as a regularized max-min problem. For both problems, we develop approximation algorithms with theoretical guarantees. Experiments on real-data and controlled clustered benchmarks show that the proposed attack is effective in representative low-to-moderate budget regimes and can induce downstream task-performance loss. The proposed defense improves the robustness--mitigation trade-off in structured settings, while also revealing the parameter sensitivity of robust protection on real data.

Can financial news reliably predict short-term stock movements? Despite advances in large language models, this question remains unresolved. We revisit this problem using a zero-shot natural language processing framework, investigating whether models can extract actionable signals from financial news without domain-specific training. We design a structured pipeline that combines zero-shot natural language inference with temporal aggregation, explicitly modelling recency and event-dependent impact horizons when integrating information across articles. To address the need for transparency in high-stakes settings, we introduce a multi-layered explainability framework that links predictions to token-level, article-level, and aggregate evidence, and produces grounded natural language rationales. Across multiple models and prediction horizons, we find that zero-shot approaches consistently fail to outperform simple baselines, with particularly weak performance on negative movements, suggesting deeper structural limitations in mapping news sentiment to short-term price dynamics. However, explainability signals reliably distinguish between trustworthy and unreliable predictions, offering practical value even when accuracy is limited. These findings highlight the limits of zero-shot financial NLP and motivate a shift toward decision-support systems that prioritise transparency and uncertainty awareness. Code: https://github.com/alimert05/zero-shot-stock-xai

Internet of Things (IoT) deployments combine heterogeneous, resource-constrained devices with weak security configurations, exposed services, limited logging, patching constraints, and long lifecycles. Signature- and threshold-based controls remain useful baselines, but they are insufficient as standalone mechanisms in dynamic IoT networks. Likewise, offline artificial intelligence (AI) benchmark performance alone does not establish operational deployability. This article presents a conceptual framework and research agenda for a Linux-based IoT edge gateway that combines resource-aware flow-level AI-assisted risk scoring, event-level explainability, and bounded mitigation through eBPF/XDP. The controller applies reversible, time-limited actions subject to critical-device safeguards, updates packet-level enforcement state, and records structured logs. The architecture separates complex reasoning and policy control in user space from concise packet-handling decisions in the kernel. It also defines a future hardware-aware evaluation pathway covering detection quality, resource cost, response timing, rollback behaviour, and legitimate-traffic preservation. The paper does not report new experimental measurements or claim measured superiority or completed real-time performance.

Evaluating XAI Support From A Hierarchical Reinforcement Learning Policy in Human-Agent Collaboration

Mateus Levi Simões Fernandes, Alberto Sardinha

Explainable AI (XAI) has shown promise for human-agent collaboration, yet results rely on hand-crafted policies in custom environments, limiting generalizability to state-of-the-art teaming research. We provide the first systematic evaluation of XAI support generated from an intrinsically explainable learned policy in an established benchmark. Using the Hierarchical Ad Hoc Agents (HA$^2$) architecture in Overcooked-AI, we generate real-time explanations from hierarchical subtask selections, delivered through text or audio via a novel trigger-based system. Our between-subjects experiment (n=38) found no significant performance effects, though participants with explanations showed trends toward faster performance improvement. More notably, audio explanations produced a significant reduction in participants' working-alliance bond with the agent -- an effect absent under the text modality -- suggesting that spoken explanations activate partnership expectations the underlying reactive policy cannot meet. We provide the first modality comparison in real-time human-agent collaboration and establish a baseline methodology for evaluating intrinsically explainable reinforcement learning architectures in benchmark environments. Results point to matching explanation modality to the underlying policy's capacity of sustaining the partnership its delivery implies as a potential path for more effective collaborative XAI.

Feature interactions drive much of the predictive power of machine learning models, yet existing explanation methods only detect and quantify interactions without revealing their functional form, or visualize only restricted interaction types. We propose Surrogate-based Analysis of Interactions via Local Effect Smooths (SAILS), a model-agnostic framework that analyzes pairwise interactions through generalized additive model (GAM) surrogates fitted to the local effects of a black-box model. For each interval of a feature of interest, the surrogate smooth terms isolate the interaction components on derivative level, enabling (i) interaction detection through a heuristic derived from significance tests on smooth terms, (ii) interaction form categorization into linear, product-separable, and non-product-separable types, and (iii) tailored, interpretable visualizations for each interaction type. We empirically validate the framework through controlled simulations and a real-world task, showing its effectiveness for pairwise interactions, with limitations under strong feature correlations and higher-order interactions. SAILS fills a notable gap in the eXplainable AI (XAI) toolbox, going beyond detecting interactions alone to characterizing their functional form.

The growing complexity of self-adaptive and self-organising systems, fuelled by advances in Artificial Intelligence (AI), has made them increasingly difficult to understand and trust. While Explainable AI aims to provide insight into AI decision-making, a more advanced goal is for systems to explain themselves - an ability referred to as Self-Explainability (SX). This article presents a systematic literature review on SX, analysing existing approaches, including their domains, targets, and evaluation methods. The review develops a unified definition and taxonomy of SX and introduces Levels of Self-Explainability, providing a framework for positioning current and future research. Our results show that most SX approaches remain conceptual, with few practical implementations. Moreover, there is currently no formal or de facto standard for evaluating SX, highlighting a major research gap. This work thus establishes a foundation and roadmap for advancing Self-Explainability in complex systems.

Recent advances in deep learning have significantly enhanced the capabilities of Natural Language Processing (NLP) and Vision-Language Models (VLMs). However, these advancements come with increased vulnerabilities, notably through backdoor attacks that pose severe security threats. This thesis addresses two critical dimensions of Trustworthy AI and Efficient Multimodal Representation Learning: (1) security through analyzing, detecting, and designing backdoor attacks in NLP and VLMs, and (2) efficiency through advanced multimodal representation methods tailored for clinical and medical imaging applications.

As artificial intelligence (AI) systems are increasingly deployed across socially consequential domains, reports of AI-related harms and failures have grown in frequency and diversity. Although existing governance frameworks articulate high-level principles for responsible AI, large-scale empirical resources for tracking and analyzing real-world AI risk incidents remain limited. Existing incident collections are often manually curated, relatively small in scale, and insufficient for continuous, data-driven monitoring and downstream computational analysis. To address this need, we present RiskNet, a large-scale dataset of AI risk incidents constructed from large-scale multilingual news sources. RiskNet applies a structured pipeline for AI risk news identification, event-level report screening, incident alignment, and multi-dimensional incident classification. The resulting resource organizes dispersed news reports into incident-centered records and provides benchmark datasets for event classification, incident alignment, and incident-level risk labeling. In its current release, RiskNet covers hundreds of millions of source records and yields a large-scale collection of AI risk-related reports, including aligned incident clusters and annotated benchmark subsets. The dataset is also accessible through an online platform for browsing and exploration. We describe the data sources, processing workflow, taxonomy design, and technical validation of the resource. RiskNet is intended to support downstream research on AI safety, governance, risk analysis, and benchmarking, as well as longitudinal and cross-source analyses of AI-related harms. By providing a structured and reusable empirical resource, RiskNet helps bridge the gap between high-level governance principles and the documented realities of AI risk incidents.

Multi-agent large language model (LLM) systems are rapidly emerging, yet transparency, a cornerstone of responsible AI, remains under-defined in these distributed architectures, which have complexities of inter-agent coordination and orchestration. In this paper, we present one of the first empirical study of how early adopters of multi-agent LLM systems, who are both the builders and users, understand and practice transparency. We conducted semi-structured interviews with 13 early adopters in [Large Technology Organization] and applied thematic analysis to identify recurring patterns. Participants articulated divergent yet complementary framings of transparency, including reproducibility, debugging, boundary-setting, visualization, and auditing. These perspectives spanned questions of what transparency entails, why it matters, and how it is achieved. We synthesize these into a multidimensional framework, which is developer, user, and governance-focused positioning transparency as a situated socio-technical practice that informs future HCI and AI design and research around aligning expectations and capacities of their intended audiences.

The growing demand for transparency in automated decision-making has propelled eXplainable Artificial Intelligence (XAI) to the forefront of machine learning research. In computer vision, however, existing explanation methods often prioritize end-user accessibility at the expense of formal guarantees, leaving a critical gap between practical utility and theoretical rigor. In this paper, we address this gap by introducing OPTIMUS, a novel framework for generating concept-based visual explanations for deep classification models. OPTIMUS explanations take the form of visual heatmaps that not only remain interpretable to end users, but are grounded in the well-established theory of prime implicants, providing formal guarantees that have been largely absent from existing saliency-based methods. Specifically, OPTIMUS explanations satisfy two desirable properties: sufficiency, ensuring that the highlighted concepts provably guarantee the classifier's prediction, and minimality, ensuring that no strict subset of those concepts retains this guarantee. Together, these properties yield explanations that are both logically tight and visually coherent. We validate our approach on a visual classification benchmark, demonstrating that OPTIMUS heatmaps naturally and faithfully surface the decision-relevant concepts underlying model predictions.

For Human-AI Interaction (HAII) research to move forward, theoretical work linking psychological mechanisms to interface design is needed. Such work should extend rather than replace established HCI and automation research, adapting to the increasing autonomy and agency of AI systems. Building on prior frameworks focused on roles and levels in human interaction with automation, a gap remains from a psychological view: a task-centered, process-oriented account that links mechanisms of action regulation to concrete design and evaluation levers for human-AI coupling, expressed in a unified vocabulary for human and machine. Moreover, existing models may describe how a system is designed (e.g., function allocation in automation) but fall short in showing how this design affects human behavior. We present the Integrated Information Processing (IIP) model, a task-centered, cybernetic model that conceptualizes humans, machines, and their joint activity as coupled control loops. The IIP model uses a unified modeling language for human and artificial agents, making psychological models of action regulation accessible for AI system design. As a core feature, we argue that efficacy within a shared task is characterized by three integration qualities, input adequacy, reference consonance, and output operativity, which critically influence benchmarks of human-centeredness such as transparency and controllability. The model maps interface choices (e.g., XAI techniques) to theory-driven expectations of user behavior, guiding interface design and evaluation. To this end, we present (1) a continuity-preserving theoretical discourse that extends HAII to agency in AI; (2) the IIP model with three information-processing qualities; and (3) applications of the IIP model to exemplary use cases demonstrating implications for interface design.

The increasing adoption of distributed infrastructure systems, cloud computing, Internet of Things (IoT) technologies, and edge-based architectures has significantly expanded the cybersecurity attack surface and introduced increasingly sophisticated cyber threats. Conventional centralized intrusion detection approaches often face challenges related to scalability, data privacy, communication overhead, and limited transparency in artificial intelligence-driven decision-making processes. To address these limitations, this study proposes a Cognitive Threat Intelligence and Explainable Federated Security Analytics framework for distributed infrastructure systems. The proposed framework integrates Federated Learning (FL), Explainable Artificial Intelligence (XAI), and cognitive cybersecurity analytics to enable collaborative and privacy-preserving cyber threat detection across distributed network environments. Instead of transmitting sensitive raw network traffic data to centralized servers, local security models are independently trained at distributed nodes, where only encrypted model parameters and updates are shared through a federated aggregation mechanism. This decentralized learning architecture improves privacy protection while reducing communication dependency and centralized security risks. To enhance intelligent threat analysis, the framework incorporates machine learning and deep learning algorithms including Random Forest, XGBoost, Autoencoder