4 Search Results for "Martens, Moritz"

Document
Academic Track
DOI: 10.4230/OASIcs.SAIA.2024.12
A View on Vulnerabilites: The Security Challenges of XAI (Academic Track)

Authors: Elisabeth Pachl, Fabian Langer, Thora Markert, and Jeanette Miriam Lorenz

Published in: OASIcs, Volume 126, Symposium on Scaling AI Assessments (SAIA 2024)

Abstract
Modern deep learning methods have long been considered as black-boxes due to their opaque decision-making processes. Explainable Artificial Intelligence (XAI), however, has turned the tables: it provides insight into how these models work, promoting transparency that is crucial for accountability. Yet, recent developments in adversarial machine learning have highlighted vulnerabilities in XAI methods, raising concerns about security, reliability and trustworthiness, particularly in sensitive areas like healthcare and autonomous systems. Awareness of the potential risks associated with XAI is needed as its adoption increases, driven in part by the need to enhance compliance to regulations. This survey provides a holistic perspective on the security and safety landscape surrounding XAI, categorizing research on adversarial attacks against XAI and the misuse of explainability to enhance attacks on AI systems, such as evasion and privacy breaches. Our contribution includes identifying current insecurities in XAI and outlining future research directions in adversarial XAI. This work serves as an accessible foundation and outlook to recognize potential research gaps and define future directions. It identifies data modalities, such as time-series or graph data, and XAI methods that have not been extensively investigated for vulnerabilities in current research.
Cite as

Elisabeth Pachl, Fabian Langer, Thora Markert, and Jeanette Miriam Lorenz. A View on Vulnerabilites: The Security Challenges of XAI (Academic Track). In Symposium on Scaling AI Assessments (SAIA 2024). Open Access Series in Informatics (OASIcs), Volume 126, pp. 12:1-12:23, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{pachl_et_al:OASIcs.SAIA.2024.12,
  author =	{Pachl, Elisabeth and Langer, Fabian and Markert, Thora and Lorenz, Jeanette Miriam},
  title =	{{A View on Vulnerabilites: The Security Challenges of XAI}},
  booktitle =	{Symposium on Scaling AI Assessments (SAIA 2024)},
  pages =	{12:1--12:23},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-357-7},
  ISSN =	{2190-6807},
  year =	{2025},
  volume =	{126},
  editor =	{G\"{o}rge, Rebekka and Haedecke, Elena and Poretschkin, Maximilian and Schmitz, Anna},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.SAIA.2024.12},
  URN =		{urn:nbn:de:0030-drops-227523},
  doi =		{10.4230/OASIcs.SAIA.2024.12},
  annote =	{Keywords: Explainability, XAI, Transparency, Adversarial Machine Learning, Security, Vulnerabilities}
}
Document
Survey
DOI: 10.4230/TGDK.2.1.3
Semantic Web: Past, Present, and Future

Authors: Ansgar Scherp, Gerd Groener, Petr Škoda, Katja Hose, and Maria-Esther Vidal

Published in: TGDK, Volume 2, Issue 1 (2024): Special Issue on Trends in Graph Data and Knowledge - Part 2. Transactions on Graph Data and Knowledge, Volume 2, Issue 1

Abstract
Ever since the vision was formulated, the Semantic Web has inspired many generations of innovations. Semantic technologies have been used to share vast amounts of information on the Web, enhance them with semantics to give them meaning, and enable inference and reasoning on them. Throughout the years, semantic technologies, and in particular knowledge graphs, have been used in search engines, data integration, enterprise settings, and machine learning. In this paper, we recap the classical concepts and foundations of the Semantic Web as well as modern and recent concepts and applications, building upon these foundations. The classical topics we cover include knowledge representation, creating and validating knowledge on the Web, reasoning and linking, and distributed querying. We enhance this classical view of the so-called "Semantic Web Layer Cake" with an update of recent concepts that include provenance, security and trust, as well as a discussion of practical impacts from industry-led contributions. We conclude with an outlook on the future directions of the Semantic Web. This is a living document. If you like to contribute, please contact the first author and visit: https://github.com/ascherp/semantic-web-primer
Cite as

Ansgar Scherp, Gerd Groener, Petr Škoda, Katja Hose, and Maria-Esther Vidal. Semantic Web: Past, Present, and Future. In Special Issue on Trends in Graph Data and Knowledge - Part 2. Transactions on Graph Data and Knowledge (TGDK), Volume 2, Issue 1, pp. 3:1-3:37, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@Article{scherp_et_al:TGDK.2.1.3,
  author =	{Scherp, Ansgar and Groener, Gerd and \v{S}koda, Petr and Hose, Katja and Vidal, Maria-Esther},
  title =	{{Semantic Web: Past, Present, and Future}},
  journal =	{Transactions on Graph Data and Knowledge},
  pages =	{3:1--3:37},
  ISSN =	{2942-7517},
  year =	{2024},
  volume =	{2},
  number =	{1},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/TGDK.2.1.3},
  URN =		{urn:nbn:de:0030-drops-198607},
  doi =		{10.4230/TGDK.2.1.3},
  annote =	{Keywords: Linked Open Data, Semantic Web Graphs, Knowledge Graphs}
}
Document
DOI: 10.4230/LIPIcs.FSCD.2016.19
The Intersection Type Unification Problem

Authors: Andrej Dudenhefner, Moritz Martens, and Jakob Rehof

Published in: LIPIcs, Volume 52, 1st International Conference on Formal Structures for Computation and Deduction (FSCD 2016)

Abstract
The intersection type unification problem is an important component in proof search related to several natural decision problems in intersection type systems. It is unknown and remains open whether the unification problem is decidable. We give the first nontrivial lower bound for the problem by showing (our main result) that it is exponential time hard. Furthermore, we show that this holds even under rank 1 solutions (substitutions whose codomains are restricted to contain rank 1 types). In addition, we provide a fixed-parameter intractability result for intersection type matching (one-sided unification), which is known to be NP-complete. We place the intersection type unification problem in the context of unification theory. The equational theory of intersection types can be presented as an algebraic theory with an ACI (associative, commutative, and idempotent) operator (intersection type) combined with distributivity properties with respect to a second operator (function type). Although the problem is algebraically natural and interesting, it appears to occupy a hitherto unstudied place in the theory of unification, and our investigation of the problem suggests that new methods are required to understand the problem. Thus, for the lower bound proof, we were not able to reduce from known results in ACI-unification theory and use game-theoretic methods for two-player tiling games.
Cite as

Andrej Dudenhefner, Moritz Martens, and Jakob Rehof. The Intersection Type Unification Problem. In 1st International Conference on Formal Structures for Computation and Deduction (FSCD 2016). Leibniz International Proceedings in Informatics (LIPIcs), Volume 52, pp. 19:1-19:16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2016)

Copy BibTex To Clipboard

@InProceedings{dudenhefner_et_al:LIPIcs.FSCD.2016.19,
  author =	{Dudenhefner, Andrej and Martens, Moritz and Rehof, Jakob},
  title =	{{The Intersection Type Unification Problem}},
  booktitle =	{1st International Conference on Formal Structures for Computation and Deduction (FSCD 2016)},
  pages =	{19:1--19:16},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-010-1},
  ISSN =	{1868-8969},
  year =	{2016},
  volume =	{52},
  editor =	{Kesner, Delia and Pientka, Brigitte},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FSCD.2016.19},
  URN =		{urn:nbn:de:0030-drops-59955},
  doi =		{10.4230/LIPIcs.FSCD.2016.19},
  annote =	{Keywords: Intersection Type, Equational Theory, Unification, Tiling, Complexity}
}
Document
DOI: 10.4230/LIPIcs.CSL.2012.243
Bounded Combinatory Logic

Authors: Boris Düdder, Moritz Martens, Jakob Rehof, and Pawel Urzyczyn

Published in: LIPIcs, Volume 16, Computer Science Logic (CSL'12) - 26th International Workshop/21st Annual Conference of the EACSL (2012)

Abstract
In combinatory logic one usually assumes a fixed set of basic combinators (axiom schemes), usually K and S. In this setting the set of provable formulas (inhabited types) is PSPACE-complete in simple types and undecidable in intersection types. When arbitrary sets of axiom schemes are considered, the inhabitation problem is undecidable even in simple types (this is known as Linial-Post theorem). k-bounded combinatory logic with intersection types arises from combinatory logic by imposing the bound k on the depth of types (formulae) which may be substituted for type variables in axiom schemes. We consider the inhabitation (provability) problem for k-bounded combinatory logic: Given an arbitrary set of typed combinators and a type tau, is there a combinatory term of type tau in k-bounded combinatory logic? Our main result is that the problem is (k+2)-EXPTIME complete for k-bounded combinatory logic with intersection types, for every fixed k (and hence non-elementary when k is a parameter). We also show that the problem is EXPTIME-complete for simple types, for all k. Theoretically, our results give new insight into the expressive power of intersection types. From an application perspective, our results are useful as a foundation for composition synthesis based on combinatory logic.
Cite as

Boris Düdder, Moritz Martens, Jakob Rehof, and Pawel Urzyczyn. Bounded Combinatory Logic. In Computer Science Logic (CSL'12) - 26th International Workshop/21st Annual Conference of the EACSL. Leibniz International Proceedings in Informatics (LIPIcs), Volume 16, pp. 243-258, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2012)

Copy BibTex To Clipboard

@InProceedings{dudder_et_al:LIPIcs.CSL.2012.243,
  author =	{D\"{u}dder, Boris and Martens, Moritz and Rehof, Jakob and Urzyczyn, Pawel},
  title =	{{Bounded Combinatory Logic}},
  booktitle =	{Computer Science Logic (CSL'12) - 26th International Workshop/21st Annual Conference of the EACSL},
  pages =	{243--258},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-939897-42-2},
  ISSN =	{1868-8969},
  year =	{2012},
  volume =	{16},
  editor =	{C\'{e}gielski, Patrick and Durand, Arnaud},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CSL.2012.243},
  URN =		{urn:nbn:de:0030-drops-36763},
  doi =		{10.4230/LIPIcs.CSL.2012.243},
  annote =	{Keywords: Intersection types, Inhabitation, Composition synthesis}
}
  • Refine by Type
  • 4 Document/PDF
  • 2 Document/HTML

  • Refine by Publication Year
  • 1 2025
  • 1 2024
  • 1 2016
  • 1 2012

  • Refine by Author
  • 2 Martens, Moritz
  • 2 Rehof, Jakob
  • 1 Dudenhefner, Andrej
  • 1 Düdder, Boris
  • 1 Groener, Gerd
  • Show More...

  • Refine by Series/Journal
  • 2 LIPIcs
  • 1 OASIcs
  • 1 TGDK

  • Refine by Classification
  • 1 Computing methodologies → Knowledge representation and reasoning
  • 1 Computing methodologies → Machine learning
  • 1 Computing methodologies → Ontology engineering
  • 1 Information systems → Markup languages
  • 1 Information systems → Semantic web description languages

  • Refine by Keyword
  • 1 Adversarial Machine Learning
  • 1 Complexity
  • 1 Composition synthesis
  • 1 Equational Theory
  • 1 Explainability
  • Show More...

Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact