3 Search Results for "Mentens, Nele"

Document
DOI: 10.4230/LIPIcs.SAT.2025.32
Efficient Certified Reasoning for Binarized Neural Networks

Authors: Jiong Yang, Yong Kiam Tan, Mate Soos, Magnus O. Myreen, and Kuldeep S. Meel

Published in: LIPIcs, Volume 341, 28th International Conference on Theory and Applications of Satisfiability Testing (SAT 2025)

Abstract
Neural networks have emerged as essential components in safety-critical applications - these use cases demand complex, yet trustworthy computations. Binarized Neural Networks (BNNs) are a type of neural network where each neuron is constrained to a Boolean value; they are particularly well-suited for safety-critical tasks because they retain much of the computational capacities of full-scale (floating-point or quantized) deep neural networks, but remain compatible with satisfiability solvers for qualitative verification and with model counters for quantitative reasoning. However, existing methods for BNN analysis suffer from either limited scalability or susceptibility to soundness errors, which hinders their applicability in real-world scenarios. In this work, we present a scalable and trustworthy approach for both qualitative and quantitative verification of BNNs. Our approach introduces a native representation of BNN constraints in a custom-designed solver for qualitative reasoning, and in an approximate model counter for quantitative reasoning. We further develop specialized proof generation and checking pipelines with native support for BNN constraint reasoning, ensuring trustworthiness for all of our verification results. Empirical evaluations on a BNN robustness verification benchmark suite demonstrate that our certified solving approach achieves a 9× speedup over prior certified CNF and PB-based approaches, and our certified counting approach achieves a 218× speedup over the existing CNF-based baseline. In terms of coverage, our pipeline produces fully certified results for 99% and 86% of the qualitative and quantitative reasoning queries on BNNs, respectively. This is in sharp contrast to the best existing baselines which can fully certify only 62% and 4% of the queries, respectively.
Cite as

Jiong Yang, Yong Kiam Tan, Mate Soos, Magnus O. Myreen, and Kuldeep S. Meel. Efficient Certified Reasoning for Binarized Neural Networks. In 28th International Conference on Theory and Applications of Satisfiability Testing (SAT 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 341, pp. 32:1-32:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{yang_et_al:LIPIcs.SAT.2025.32,
  author =	{Yang, Jiong and Tan, Yong Kiam and Soos, Mate and Myreen, Magnus O. and Meel, Kuldeep S.},
  title =	{{Efficient Certified Reasoning for Binarized Neural Networks}},
  booktitle =	{28th International Conference on Theory and Applications of Satisfiability Testing (SAT 2025)},
  pages =	{32:1--32:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-381-2},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{341},
  editor =	{Berg, Jeremias and Nordstr\"{o}m, Jakob},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.SAT.2025.32},
  URN =		{urn:nbn:de:0030-drops-237665},
  doi =		{10.4230/LIPIcs.SAT.2025.32},
  annote =	{Keywords: Neural network verification, proof certification, SAT solving, approximate model counting}
}
Document
DOI: 10.4230/DagRep.12.10.106
Intelligent Security: Is "AI for Cybersecurity" a Blessing or a Curse (Dagstuhl Seminar 22412)

Authors: Nele Mentens, Stjepan Picek, and Ahmad-Reza Sadeghi

Published in: Dagstuhl Reports, Volume 12, Issue 10 (2023)

Abstract
This report documents the outcomes of Dagstuhl Seminar 22412 "Intelligent Security: Is "AI for Cybersecurity" a Blessing or a Curse". The seminar brought together 25 attendees from 10 countries (Canada, Croatia, Czech Republic, France, Germany, Netherlands, Singapore, Sweden, Switzerland, and the USA). There were 17 male and 8 female participants. Three participants were from the industry, and the rest were from academia. The gathered researchers are actively working in the domains of artificial intelligence and cybersecurity, emphasizing hardware security, fuzzing, physical security, and network security. The seminar aims to foster sharing experiences and best practices between various cybersecurity applications and understand how and when certain approaches are transferable. The first two days were devoted to 20-minute self-introductions by participants to achieve these goals. At the end of the second day, we made a list of topics that were decided to be the focus of the seminar and that will be discussed in the groups in the next few days. On the third and fourth days, the work was conducted in four discussion groups where at the end of each day, all participants gathered to report the results from the discussion groups and to align the goals. On the last day, we again worked in one group to summarize the findings and foster networking among participants. A hike was organized in the afternoon of the third day. The seminar was a success. The participants actively participated in the working groups and the discussions and went home with new ideas and collaborators. This report gathers the abstracts of the presented talks and the conclusions from the discussion groups, which we consider relevant contributions toward better interdisciplinary research on artificial intelligence and cybersecurity.
Cite as

Nele Mentens, Stjepan Picek, and Ahmad-Reza Sadeghi. Intelligent Security: Is "AI for Cybersecurity" a Blessing or a Curse (Dagstuhl Seminar 22412). In Dagstuhl Reports, Volume 12, Issue 10, pp. 106-128, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@Article{mentens_et_al:DagRep.12.10.106,
  author =	{Mentens, Nele and Picek, Stjepan and Sadeghi, Ahmad-Reza},
  title =	{{Intelligent Security: Is "AI for Cybersecurity" a Blessing or a Curse (Dagstuhl Seminar 22412)}},
  pages =	{106--128},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2023},
  volume =	{12},
  number =	{10},
  editor =	{Mentens, Nele and Picek, Stjepan and Sadeghi, Ahmad-Reza},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.12.10.106},
  URN =		{urn:nbn:de:0030-drops-178229},
  doi =		{10.4230/DagRep.12.10.106},
  annote =	{Keywords: Cybersecurity, Artificial Intelligence, Hardware Security, Machine Learning, Explainability}
}
Document
DOI: 10.4230/DagSemProc.10281.11
Secure remote reconfiguration of FPGAs

Authors: Nele Mentens, Jo Vliegen, An Braeken, Abdellah Touhafi, Karel Wouters, and Ingrid Verbauwhede

Published in: Dagstuhl Seminar Proceedings, Volume 10281, Dynamically Reconfigurable Architectures (2010)

Abstract
This paper presents a solution for secure remote reconfiguration of FPGAs. Communicating the bitstream has to be done in a secure manner to prevent an attacker from reading or altering the bitstream. We propose a setup in which the FPGA is the single device in the system's zone-of-trust. The result is an FPGA architecture that is divided into a static and a dynamic region. The static region holds the communication, security and reconfiguration facilities, while the dynamic region contains the targeted application.
Cite as

Nele Mentens, Jo Vliegen, An Braeken, Abdellah Touhafi, Karel Wouters, and Ingrid Verbauwhede. Secure remote reconfiguration of FPGAs. In Dynamically Reconfigurable Architectures. Dagstuhl Seminar Proceedings, Volume 10281, pp. 1-4, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2010)

Copy BibTex To Clipboard

@InProceedings{mentens_et_al:DagSemProc.10281.11,
  author =	{Mentens, Nele and Vliegen, Jo and Braeken, An and Touhafi, Abdellah and Wouters, Karel and Verbauwhede, Ingrid},
  title =	{{Secure remote reconfiguration of FPGAs}},
  booktitle =	{Dynamically Reconfigurable Architectures},
  pages =	{1--4},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2010},
  volume =	{10281},
  editor =	{Peter M. Athanas and J\"{u}rgen Becker and J\"{u}rgen Teich and Ingrid Verbauwhede},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.10281.11},
  URN =		{urn:nbn:de:0030-drops-28391},
  doi =		{10.4230/DagSemProc.10281.11},
  annote =	{Keywords: FPGA, cryptography, security, remote configuration}
}
  • Refine by Type
  • 3 Document/PDF
  • 2 Document/HTML

  • Refine by Publication Year
  • 1 2025
  • 1 2023
  • 1 2010

  • Refine by Author
  • 2 Mentens, Nele
  • 1 Braeken, An
  • 1 Meel, Kuldeep S.
  • 1 Myreen, Magnus O.
  • 1 Picek, Stjepan
  • Show More...

  • Refine by Series/Journal
  • 1 LIPIcs
  • 1 DagRep
  • 1 DagSemProc

  • Refine by Classification
  • 2 Computing methodologies → Artificial intelligence
  • 1 Computer systems organization → Real-time systems
  • 1 Computing methodologies → Machine learning
  • 1 Computing methodologies → Neural networks
  • 1 Security and privacy → Cryptography
  • Show More...

  • Refine by Keyword
  • 1 Artificial Intelligence
  • 1 Cybersecurity
  • 1 Explainability
  • 1 FPGA
  • 1 Hardware Security
  • 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
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact