arXiv subjects

Holger Hermanns

Publications and source records attributed to Holger Hermanns.

At least 19 recordsLinked to original sources

arXiv2026

Stability Checking of Markov Jump Linear Systems via Probabilistic Temporal Logic (Extended Version)

Markov jump linear systems (MJLSs) model dynamical phenomena subject to random switching among multiple linear modes, driven by an underlying Markov chain. Classical notions such as mean and mean-square stability characterize the long-term asymptotic behaviour of the first and second moments of an MJLS, but they can be overly conservative or even misleading when only a specific subset of initial conditions is of interest. We tackle this challenge through the lens of model checking, where reasoning about specific sets of initial conditions is intrinsic to the approach. We begin by formalizing probabilistic computation tree logic (PCTL) on MJLSs, enabling the specification of state-based temporal properties for these systems. Building on this foundation, we extend the logic to capture moment-based stability properties relative to a prescribed set of initial states. While we ultimately do not obtain a decision procedure for the entire base logic, the logical extensions can be handled -- albeit with some technical subtleties -- by exploiting linear-algebraic techniques.

cs.LO↗

arXiv2026

Bridging the Disciplinary Gap in Explainable AI: From Abstract Desiderata to Concrete Tasks

Explainable AI (XAI) is often criticized for failing to satisfy broad desiderata (e.g., fairness, accountability) and for limited practical value to stakeholders. This challenge partly arises because researchers across disciplines prioritize different sets of desiderata that remain underspecified and context-dependent, yet expect XAI to satisfy them simultaneously, resulting in fragmented and sometimes incompatible operationalizations. We argue that many desiderata are not independent, but instead form dependency structures in which higher-level goals (\emph{e.g.}, trust, accountability) rely on more foundational properties (\emph{e.g.}, faithfulness, robustness). Some desiderata are multi-faceted and are best understood within these structures. In particular, instead of addressing all desiderata at once, we focus on subsets of dependency structures and translate them into concrete XAI tasks, thereby decomposing research questions into benchmarkable and solvable units. To this end, we propose a three-axis taxonomy (\emph{target}, \emph{functional role}, and \emph{mode of justification}) and a three-step framework for deriving well-scoped, benchmarkable XAI tasks. Our approach builds on a systematic literature review and conceptual analysis, and supports clarifying desiderata, identifying dependencies, scoping feasibility, and delimiting the design space to derive concrete XAI tasks from abstract desiderata. We illustrate its utility through two explanatory cases, showing how the taxonomy and framework guide systematic task design and evaluation in XAI. {\color{red}{This is a preprint of a paper that will appear in AISoLA 2026.}}

cs.CY↗

arXiv2026

Over-approximation of weakly-hard constraints for control systems verification (Extended)

A hard real-time system cannot miss any deadline. A weakly-hard real-time system, on the contrary, is designed to tolerate a specific number of deadline misses. For instance, the AnyMiss(2, 300) weakly-hard constraint stipulates that in every window of 300 consecutive jobs, at most 2 deadlines are missed. The weakly-hard model is the state-of-the-art for industrial dependability-by-design of control systems that tolerate deterministic failures. Weakly-hard constraints correspond to regular languages. The size of the minimal finite state machine that recognizes whether a string satisfies the constraint (about 45k states for AnyMiss(2, 300)) is a notorious impediment for the verification of control system properties. This paper discusses an over-approximation of the language that allows us to provide sound safety guarantees for control systems under deadline misses that would be out of reach using the minimal finite state machine. We present a compressed language acceptor and prove that it simulates the original finite state machine. We study language cardinality properties, and report on empirical results that show how the new acceptor can be embedded in the control design workflow, leading to verifying safety for systems for which the state-of-the-art tools do not provide answers.

eess.SY↗

arXiv2026

SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability

Explainable AI (XAI) is crucial for building transparent and trustworthy machine learning systems, especially in high-stakes domains. Concept Bottleneck Models (CBMs) have emerged as a promising ante-hoc approach that provides interpretable, concept-level explanations by explicitly modeling human-understandable concepts. However, existing CBMs often suffer from poor locality faithfulness, failing to spatially align concepts with meaningful image regions, which limits their interpretability and reliability. In this work, we propose SL-CBM (CBM with Semantic Locality), a novel extension that enforces locality faithfulness by generating spatially coherent saliency maps at both concept and class levels. SL-CBM integrates a 1x1 convolutional layer with a cross-attention mechanism to enhance alignment between concepts, image regions, and final predictions. Unlike prior methods, SL-CBM produces faithful saliency maps inherently tied to the model's internal reasoning, facilitating more effective debugging and intervention. Extensive experiments on image datasets demonstrate that SL-CBM substantially improves locality faithfulness, explanation quality, and intervention efficacy while maintaining competitive classification accuracy. Our ablation studies highlight the importance of contrastive and entropy-based regularization for balancing accuracy, sparsity, and faithfulness. Overall, SL-CBM bridges the gap between concept-based reasoning and spatial explainability, setting a new standard for interpretable and trustworthy concept-based models.

cs.AI↗

arXiv2025

POMDP-Based Routing for DTNs with Partial Knowledge and Dependent Failures

Routing in Delay-Tolerant Networks (DTNs) is inherently challenging due to sparse connectivity, long delays, and frequent disruptions. While Markov Decision Processes (MDPs) have been used to model uncertainty, they assume full state observability - an assumption that breaks down in partitioned DTNs, where each node operates with inherently partial knowledge of the network state. In this work, we investigate the role of Partially Observable Markov Decision Processes (POMDPs) for DTN routing under uncertainty. We introduce and evaluate a novel model: Dependent Node Failures (DNF), which captures correlated node failures via repairable node states modeled as Continuous-Time Markov Chains (CTMCs). We implement the model using JuliaPOMDP and integrate it with DTN simulations via DtnSim. Our evaluation demonstrates that POMDP-based routing yields improved delivery ratios and delay performance under uncertain conditions while maintaining scalability. These results highlight the potential of POMDPs as a principled foundation for decision-making in future DTN deployments.

cs.NI↗

arXiv2025

A Workflow for Full Traceability of AI Decisions

An ever increasing number of high-stake decisions are made or assisted by automated systems employing brittle artificial intelligence technology. There is a substantial risk that some of these decision induce harm to people, by infringing their well-being or their fundamental human rights. The state-of-the-art in AI systems makes little effort with respect to appropriate documentation of the decision process. This obstructs the ability to trace what went into a decision, which in turn is a prerequisite to any attempt of reconstructing a responsibility chain. Specifically, such traceability is linked to a documentation that will stand up in court when determining the cause of some AI-based decision that inadvertently or intentionally violates the law. This paper takes a radical, yet practical, approach to this problem, by enforcing the documentation of each and every component that goes into the training or inference of an automated decision. As such, it presents the first running workflow supporting the generation of tamper-proof, verifiable and exhaustive traces of AI decisions. In doing so, we expand the DBOM concept into an effective running workflow leveraging confidential computing technology. We demonstrate the inner workings of the workflow in the development of an app to tell poisonous and edible mushrooms apart, meant as a playful example of high-stake decision support.

cs.AI↗

arXiv2025

Automata Learning -- Expect Delays!

This paper studies active automata learning (AAL) in the presence of stochastic delays. We consider Mealy machines that have stochastic delays associated with each transition and explore how the learner can efficiently arrive at faithful estimates of those machines, the precision of which crucially relies on repetitive sampling of transition delays. While it is possible to na\"ively integrate the delay sampling into AAL algorithms such as $L^*$, this leads to considerable oversampling near the root of the state space. We address this problem by separating conceptually the learning of behavior and delays such that the learner uses the information gained while learning the logical behavior to arrive at efficient input sequences for collecting the needed delay samples. We put emphasis on treating cases in which identical input/output behaviors might stem from distinct delay characteristics. Finally, we provide empirical evidence that our method outperforms the na\"ive baseline across a wide range of benchmarks and investigate its applicability in a realistic setting by studying the join order in a relational database.

cs.FL↗

arXiv2025

Dirty Bits in Low-Earth Orbit: The Carbon Footprint of Launching Computers

Low-Earth Orbit (LEO) satellites are increasingly proposed for communication and in-orbit computing, achieving low-latency global services. However, their sustainability remains largely unexamined. This paper investigates the carbon footprint of computing in space, focusing on lifecycle emissions from launch over orbital operation to re-entry. We present ESpaS, a lightweight tool for estimating carbon intensities across CPU usage, memory, and networking in orbital vs. terrestrial settings. Three worked examples compare (i) launch technologies (state-of-the-art rocket vs. potential next generation), (ii) operational emissions of data center workloads in orbit and on the ground and, (iii) in-orbit aggregation with raw data transmission. Results show that, even under optimistic assumptions, in-orbit systems incur significantly higher carbon costs - primarily due to embodied emissions from launch and re-entry. Our findings advocate for carbon-aware design principles and regulatory oversight in developing sustainable digital infrastructure in orbit.

cs.CY↗

arXiv2025

Revisiting Physically Realizable Adversarial Object Attack against LiDAR-based Detection: Clarifying Problem Formulation and Experimental Protocols

Adversarial robustness in LiDAR-based 3D object detection is a critical research area due to its widespread application in real-world scenarios. While many digital attacks manipulate point clouds or meshes, they often lack physical realizability, limiting their practical impact. Physical adversarial object attacks remain underexplored and suffer from poor reproducibility due to inconsistent setups and hardware differences. To address this, we propose a device-agnostic, standardized framework that abstracts key elements of physical adversarial object attacks, supports diverse methods, and provides open-source code with benchmarking protocols in simulation and real-world settings. Our framework enables fair comparison, accelerates research, and is validated by successfully transferring simulated attacks to a physical LiDAR system. Beyond the framework, we offer insights into factors influencing attack success and advance understanding of adversarial robustness in real-world LiDAR perception.

cs.CV↗

arXiv2025

On the Role of AI in Managing Satellite Constellations: Insights from the ConstellAI Project

The rapid expansion of satellite constellations in near-Earth orbits presents significant challenges in satellite network management, requiring innovative approaches for efficient, scalable, and resilient operations. This paper explores the role of Artificial Intelligence (AI) in optimizing the operation of satellite mega-constellations, drawing from the ConstellAI project funded by the European Space Agency (ESA). A consortium comprising GMV GmbH, Saarland University, and Thales Alenia Space collaborates to develop AI-driven algorithms and demonstrates their effectiveness over traditional methods for two crucial operational challenges: data routing and resource allocation. In the routing use case, Reinforcement Learning (RL) is used to improve the end-to-end latency by learning from historical queuing latency, outperforming classical shortest path algorithms. For resource allocation, RL optimizes the scheduling of tasks across constellations, focussing on efficiently using limited resources such as battery and memory. Both use cases were tested for multiple satellite constellation configurations and operational scenarios, resembling the real-life spacecraft operations of communications and Earth observation satellites. This research demonstrates that RL not only competes with classical approaches but also offers enhanced flexibility, scalability, and generalizability in decision-making processes, which is crucial for the autonomous and intelligent management of satellite fleets. The findings of this activity suggest that AI can fundamentally alter the landscape of satellite constellation management by providing more adaptive, robust, and cost-effective solutions.

cs.LG↗

arXiv2024

Configuration Monitor Synthesis

The observable behavior of a system usually carries useful information about its internal state, properties, and potential future behaviors. In this paper, we introduce configuration monitoring to determine an unknown configuration of a running system based on observations of its behavior. We develop a modular and generic pipeline to synthesize automata-theoretic configuration monitors from a featured transition system model of the configurable system to be monitored. The pipeline further allows synthesis under partial observability and network-induced losses as well as predictive configuration monitors taking the potential future behavior of a system into account. Beyond the novel application of configuration monitoring, we show that our approach also generalizes and unifies existing work on runtime monitoring and fault diagnosis, which aim at detecting the satisfaction or violation of properties and the occurrence of faults, respectively. We empirically demonstrate the efficacy of our approach with a case study on configuration monitors synthesized from configurable systems community benchmarks.

cs.FL↗

arXiv2024

A Stability-first Approach to Running TCP over Starlink

The end-to-end connectivity patterns between two points on Earth are highly volatile if mediated via a Low-Earth orbit (LEO) satellite constellation. This is rooted in the enormous speeds at which satellites in LEO must travel relative to the Earth's surface. While changes in end-to-end routes are rare events in stationary and terrestrial applications, they are a dominating factor for connection-oriented services running over LEO constellations and mega-constellations. This paper discusses how TCP-over-constellations is affected by the need for rerouting and how orbital route selection algorithms impact the end-to-end performance of communication. In contrast to the state of the art that primarily optimizes for instantaneous shortest routes (i.e. lowest delay), we propose several algorithms that have route stability and longevity in their focus. We show that this shift in focus comes with vastly improved end-to-end communication performance, and we discuss peculiar effects of the typical TCP-like implementations, taking inspiration from the Starlink constellation in our empirical investigations. The spectrum of algorithms proposed provides a basis for co-designing suitable orbital route selection algorithms and tailored transport control algorithms.

cs.NI↗

arXiv2024

AI Act for the Working Programmer

The European AI Act is a new, legally binding instrument that will enforce certain requirements on the development and use of AI technology potentially affecting people in Europe. It can be expected that the stipulations of the Act, in turn, are going to affect the work of many software engineers, software testers, data engineers, and other professionals across the IT sector in Europe and beyond. The 113 articles, 180 recitals, and 13 annexes that make up the Act cover 144 pages. This paper aims at providing an aid for navigating the Act from the perspective of some professional in the software domain, termed "the working programmer", who feels the need to know about the stipulations of the Act.

cs.CY↗

arXiv2024

Eidos: Efficient, Imperceptible Adversarial 3D Point Clouds

Classification of 3D point clouds is a challenging machine learning (ML) task with important real-world applications in a spectrum from autonomous driving and robot-assisted surgery to earth observation from low orbit. As with other ML tasks, classification models are notoriously brittle in the presence of adversarial attacks. These are rooted in imperceptible changes to inputs with the effect that a seemingly well-trained model ends up misclassifying the input. This paper adds to the understanding of adversarial attacks by presenting Eidos, a framework providing Efficient Imperceptible aDversarial attacks on 3D pOint cloudS. Eidos supports a diverse set of imperceptibility metrics. It employs an iterative, two-step procedure to identify optimal adversarial examples, thereby enabling a runtime-imperceptibility trade-off. We provide empirical evidence relative to several popular 3D point cloud classification models and several established 3D attack methods, showing Eidos' superiority with respect to efficiency as well as imperceptibility.

cs.CV↗

arXiv2024

On the Quest for Effectiveness in Human Oversight: Interdisciplinary Perspectives

Human oversight is currently discussed as a potential safeguard to counter some of the negative aspects of high-risk AI applications. This prompts a critical examination of the role and conditions necessary for what is prominently termed effective or meaningful human oversight of these systems. This paper investigates effective human oversight by synthesizing insights from psychological, legal, philosophical, and technical domains. Based on the claim that the main objective of human oversight is risk mitigation, we propose a viable understanding of effectiveness in human oversight: for human oversight to be effective, the oversight person has to have (a) sufficient causal power with regard to the system and its effects, (b) suitable epistemic access to relevant aspects of the situation, (c) self-control, and (d) fitting intentions for their role. Furthermore, we argue that this is equivalent to saying that an oversight person is effective if and only if they are morally responsible and have fitting intentions. Against this backdrop, we suggest facilitators and inhibitors of effectiveness in human oversight when striving for practical applicability. We discuss factors in three domains, namely, the technical design of the system, individual factors of oversight persons, and the environmental circumstances in which they operate. Finally, this paper scrutinizes the upcoming AI Act of the European Union -- in particular Article 14 on Human Oversight -- as an exemplary regulatory framework in which we study the practicality of our understanding of effective human oversight. By analyzing the provisions and implications of the European AI Act proposal, we pinpoint how far that proposal aligns with our analyses regarding effective human oversight as well as how it might get enriched by our conceptual understanding of effectiveness in human oversight.

cs.CY↗

arXiv2023

Software Doping Analysis for Human Oversight

This article introduces a framework that is meant to assist in mitigating societal risks that software can pose. Concretely, this encompasses facets of software doping as well as unfairness and discrimination in high-risk decision-making systems. The term software doping refers to software that contains surreptitiously added functionality that is against the interest of the user. A prominent example of software doping are the tampered emission cleaning systems that were found in millions of cars around the world when the diesel emissions scandal surfaced. The first part of this article combines the formal foundations of software doping analysis with established probabilistic falsification techniques to arrive at a black-box analysis technique for identifying undesired effects of software. We apply this technique to emission cleaning systems in diesel cars but also to high-risk systems that evaluate humans in a possibly unfair or discriminating way. We demonstrate how our approach can assist humans-in-the-loop to make better informed and more responsible decisions. This is to promote effective human oversight, which will be a central requirement enforced by the European Union's upcoming AI Act. We complement our technical contribution with a juridically, philosophically, and psychologically informed perspective on the potential problems caused by such systems.

cs.CY↗

arXiv2023

Distributed On-Demand Routing for LEO Mega-Constellations: A Starlink Case Study

The design and launch of large-scale satellite networks create an imminent demand for efficient and delay-minimising routing methods. With the rising number of satellites in such constellations, pre-computing all shortest routes between all satellites and for all times becomes more and more infeasible due to space and time limitations. Even though distributed on-demand routing methods were developed for specific LEO satellite network configurations, they are not suited for increasingly popular mega-constellations based on Walker Delta formations. The contributions of this paper are twofold. First, we introduce a formal model that mathematically captures the time-evolving locations of satellites in a Walker Delta constellation and use it to establish a formula to compute the minimum number of ISL hops between two given satellites. In the second part, we present an on-demand hop-count-based routing algorithm that approximates the optimal path while achieving superior performance compared to classical shortest-path algorithms like Dijkstra.

cs.NI↗

arXiv2023

On the Foundations of Cycles in Bayesian Networks

Bayesian networks (BNs) are a probabilistic graphical model widely used for representing expert knowledge and reasoning under uncertainty. Traditionally, they are based on directed acyclic graphs that capture dependencies between random variables. However, directed cycles can naturally arise when cross-dependencies between random variables exist, e.g., for modeling feedback loops. Existing methods to deal with such cross-dependencies usually rely on reductions to BNs without cycles. These approaches are fragile to generalize, since their justifications are intermingled with additional knowledge about the application context. In this paper, we present a foundational study regarding semantics for cyclic BNs that are generic and conservatively extend the cycle-free setting. First, we propose constraint-based semantics that specify requirements for full joint distributions over a BN to be consistent with the local conditional probabilities and independencies. Second, two kinds of limit semantics that formalize infinite unfolding approaches are introduced and shown to be computable by a Markov chain construction.

cs.AI↗