Präsentationen und Vorträge

Präsentationen und Vorträge sind auf unserem Youtube-Kanal zusammengestellt.

Publikationen

2026

Moritz Kirschte, Sebastian Meiser, Saman Ardalan, and Esfandiar Mohammadi,
Private Blind Model Averaging – Distributed, Non-interactive, and Convergent, in 2026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), to appear , Mä.2026.
Datei: 2211.02003
Jeremy Boy, Antoon Purnal, Anna Pätschke, Luca Wilke, and Thomas Eisenbarth,
SLasH-DSA: Breaking SLH-DSA Using an Extensible End-To-End Rowhammer Framework, in 2026: Proceeding of the 2nd Microarchitecture Security Conference (uASC '26) , 2026.
DOI:10.46586/uasc.2026.009
Datei: 2509.13048
Johannes Liebenow, Thorsten Peinemann, and Esfandiar Mohammadi,
DP-HYPE: Distributed Differentially Private Hyperparameter Search, in Proceedings on Privacy Enhancing Technologies 2026 , PETS, 2026.
Weblink: https://arxiv.org/abs/2510.04902
Jonah Heller, Marcel Pflaeging, Thore Tiemann, and Thomas Eisenbarth,
CTRL+ALT+TLB: Exploring Microarchitectural Weird Machines on Translation Look-aside Buffers, in Proceedings of the 21th ACM Asia Conference on Computer and Communications Security, ASIA CCS 2026 , ACM, 2026. pp. 956-971.
DOI:10.1145/3779208.3785280
ISBN:979-8-4007-2356-8/2026/06
Bibtex: BibTeX
@inproceedings{heller2026ctrlalttlb,
  author       = {Jonah Heller and
                  Marcel Pflaeging and
                  Thore Tiemann and
                  Thomas Eisenbarth},
  title        = {CTRL+ALT+TLB: Exploring Microarchitectural Weird Machines on Translation Look-aside Buffers},
  booktitle    = {Proceedings of the 21th {ACM} Asia Conference on Computer and Communications
                  Security, {ASIA} {CCS} 2026, Bangalore, India, June 1-5, 2026},
  pages      = {956--971},
  publisher    = {{ACM}},
  year         = {2026},
  doi           = {10.1145/3779208.3785280},
  timestamp    = {Wed, 24 Nov 2025 09:46:47 +0100}
}
Moritz Kirschte, Thorsten Peinemann, Kari Kostiainen, Jan Wichelmann, Thomas Eisenbarth, and Esfandiar Mohammadi,
MammothDP: Differentially Private Boosted Decision Trees, hyperparameter-free and ready for Trusted Hardware, 2026.
Datei: MammothDP-18.pdf
Anja Rabich, Jonah Heller, Florian Sieck, and Thomas Eisenbarth,
StepOverflow: PMC Overflows on AMD SEV, in 9th Workshop on System Software for Trusted Execution (SysTEX 2026) , Apr.2026.
Jonas Sander, Anja Rabich, Nick Mahling, Felix Maurer, Jonah Heller, Qifan Wang, Thomas Eisenbarth, and David Oswald,
TrEEStealer: Stealing Decision Trees via Enclave Side Channels, 2026.
Datei: 2604.18716
Qifan Wang, Jonas Sander, Minmin Jiang, Thomas Eisenbarth, and David F. Oswald,
BarkBeetle: Stealing Decision Tree Models with Fault Injection, in Proceedings of the 2026 ACM Asia Conference on Computer and Communications Security (ASIA CCS '26) , Bangalore, India: Association for Computing Machinery, Jun.2026.
Niklas Klinger, Jonas Sander, Peterson Yuhala, Pascal Felber, and Thomas Eisenbarth,
DRAMatic Speedup: Accelerating HE Operations on a Processing-in-Memory System, IACR Communications in Cryptology , vol. 3, no. 1, 2026. International Association for Cryptologic Research.
DOI:10.62056/ahp2fh888
Niklas Zapatka, Moritz Kirschte, Sebastian Meiser, Bud Bruegger, Harald Zwingelberg, and Esfandiar Mohammadi,
Understanding Differential Privacy in Terms of Crowd Size Preservation, in Privacy Technologies and Policy, 14th Annual Privacy Forum (APF) , Cham, CH: Springer Nature Switzerland, Sep.2026. pp. 46-70.
DOI:10.1007/978-3-032-35899-8_3
ISBN:978-3-032-35899-8

2025

Philipp Schmitz, Tobias Jauch, Alex Wezel, Mohammad R. Fadiheh, Thore Tiemann, Jonah Heller, Thomas Eisenbarth, Dominik Stoffel, and Wolfgang Kunz,
Okapi: Efficiently Safeguarding Speculative Data Accesses in Sandboxed Environments, in Proceedings of the 20th ACM Asia Conference on Computer and Communications Security, ASIA CCS 2025 , ACM, 2025. pp. 1203–1218.
DOI:10.1145/3708821.3733869
Weblink: https://arxiv.org/abs/2312.08156
Bibtex: BibTeX
@inproceedings{schmitz2025okapi,
  author       = {Philipp Schmitz and
                  Tobias Jauch and
                  Alex Wezel and
                  Mohammad Rahmani Fadiheh and
                  Thore Tiemann and
                  Jonah Heller and
                  Thomas Eisenbarth and
                  Dominik Stoffel and
                  Wolfgang Kunz},
  title        = {Okapi: Efficiently Safeguarding Speculative Data Accesses in Sandboxed
                  Environments},
  booktitle    = {Proceedings of the 20th {ACM} Asia Conference on Computer and Communications
                  Security, {ASIA} {CCS} 2025, Hanoi, Vietnam, August 25-29, 2025},
  pages        = {1203--1218},
  publisher    = {{ACM}},
  year         = {2025},
  url          = {https://doi.org/10.1145/3708821.3733869},
  doi          = {10.1145/3708821.3733869},
  timestamp    = {Wed, 15 Oct 2025 19:23:47 +0200}
}
Felix Mächtle, Jan-Niclas Serr, Nils Loose, Jonas Sander, and Thomas Eisenbarth,
OCEAN: Open-World Contrastive Authorship Identification, in Applied Cryptography and Network Security (ACNS) 2025 , 2025.
Weblink: https://arxiv.org/abs/2412.05049
Bibtex: BibTeX
@misc{maechtle2024oceanopenworldcontrastiveauthorship,
      title={OCEAN: Open-World Contrastive Authorship Identification}, 
      author={Felix Mächtle and Jan-Niclas Serr and Nils Loose and Jonas Sander and Thomas Eisenbarth},
      year={2024},
      eprint={2412.05049},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2412.05049}, 
}
Felix Mächtle, Nils Loose, Jan-Niclas Serr, Jonas Sander, and Thomas Eisenbarth,
AutoStub: Genetic Programming-Based Stub Creation for Symbolic Execution, in Proceedings of the 18th ACM/IEEE International Workshop on Search-Based and Fuzz Testing, SBFT 2025 , 2025.
Jonas Sander, Sebastian Berndt, Ida Bruhns, and Thomas Eisenbarth,
Dash: Accelerating Distributed Private Convolutional Neural Network Inference with Arithmetic Garbled Circuits, IACR Transactions on Cryptographic Hardware and Embedded Systems , vol. 2025, pp. 420-449, 2025. IACR.
DOI:10.46586/tches.v2025.i1.420-449
Zane Weissman, Thore Tiemann, Thomas Eisenbarth, and Berk Sunar,
Microarchitectural Security of Firecracker VMM for Serverless Cloud Platforms, in Information Systems Security , Patil, Vishwas T. and Krishnan, Ram and Shyamasundar, Rudrapatna K., Eds. Springer Nature Switzerland, 2025. pp. 3-24.
DOI:10.1007/978-3-031-80020-7_1
ISBN:978-3-031-80020-7
Weblink: https://doi.org/10.48550/arXiv.2311.15999
Bibtex: BibTeX
@inproceedings{weissman2025firecracker,
  author    = {Weissman, Zane and
               Tiemann, Thore and
               Eisenbarth, Thomas and
               Sunar, Berk},
  title     = {Microarchitectural Security of Firecracker VMM for Serverless Cloud Platforms},
  booktitle = {Information Systems Security},
  editor    = {Patil, Vishwas T. and
               Krishnan, Ram and
               Shyamasundar, Rudrapatna K.},
  year      = {2025},
  pages     = {3--24},
  publisher = {Springer Nature Switzerland},
  isbn      = {978-3-031-80020-7},
  doi       = {10.1007/978-3-031-80020-7_1},
}
Anna Pätschke, Jan Wichelmann, and Thomas Eisenbarth,
Zebrafix: Mitigating Memory-Centric Side-Channel Leakage via Interleaving, in 28th International Symposium on Research in Attacks, Intrusions and Defenses (RAID 2025) , IEEE, 2025.
DOI:10.1109/RAID67961.2025.00063
Datei: 2502.09139
Sebastian Meiser, Debajyoti Das, Moritz Kirschte, Esfandiar Mohammadi, and Aniket Kate,
Mixnets on a tightrope: Quantifying the leakage of mix networks using a provably optimal heuristic adversary, in 2025 IEEE Symposium on Security and Privacy (SP) , Los Alamitos, CA, USA: IEEE Computer Society, 2025. pp. 4457-4475.
ISBN:979-8-3315-2236-0
Datei: SP61157.2025.00233
Christian Ewert, Andrija Neskovic, Carsten Heinz, Felix Muuss, Alexander Treff, Marc Gourjon, Rainer Buchty, Thomas Eisenbarth, Andreas Koch, Mladen Berekovic, and Saleh Mulhem,
Lightweight Authenticated Integration and In-Field Secure Operation of System-in-Package, ACM Trans. Des. Autom. Electron. Syst. , Jun. 2025. Association for Computing Machinery.
DOI:10.1145/3745780
Datei: 3745780
Thorsten Peinemann, Paula Arnold, Sebastian Berndt, Thomas Eisenbarth, and Esfandiar Mohammadi,
Non-omniscient backdoor injection with a single poison sample: Proving the one-poison hypothesis for linear regression, linear classification, and 2-layer ReLU neural networks, arXiv , Nov. 2025.
DOI:10.48550/arXiv.2508.05600
Datei: 2508.05600
Felix Maurer, Jonas Sander, and Thomas Eisenbarth,
ReDASH: Fast and Efficient Scaling in Arithmetic Garbled Circuits for Secure Outsourced Inference, in Applied Cryptography and Network Security Workshops - ACNS 2025 Satellite Workshops: AIHWS, AIoTS, QSHC, SCI, PrivCrypt, SPIQE, SiMLA, and CIMSS 2025, Munich, Germany, June 23-26, 2025, Revised Selected Papers, Part III , Mark Manulis, Eds. Springer, 2025. pp. 43—51.
DOI:10.1007/978-3-032-01823-6_3
Datei: 978-3-032-01823-6_3
Jonas Sander, and Thomas Eisenbarth,
Silenzio: Secure Non-Interactive Outsourced MLP Training, CoRR , vol. abs/2504.17785, 2025.
DOI:10.48550/ARXIV.2504.17785
Datei: arXiv.2504.17785
Jens Alich, Thomas Eisenbarth, Hossein Hadipour, Gregor Leander, Felix Mächtle, Yevhen Perehuda, Shahram Rasoolzadeh, Jonas Sander, and Cihangir Tezcan,
Attacks and Remedies for Randomness in AI: Cryptanalysis of PHILOX and THREEFRY, 2025. Cryptology ePrint Archive, Paper 2025/2161.
Datei: 2161
Yara Schütt, and Esfandiar Mohammadi,
Understanding the Theoretical Guarantees of DPM, arXiv preprint arXiv:2506.18685 , 2025.

2024

Thorsten Peinemann, Moritz Kirschte, Joshua Stock, Carlos Cotrini, and Esfandiar Mohammadi,
S-BDT: Distributed Differentially Private Boosted Decision Trees, in Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security (CCS '24) , New York, NY, USA: Association for Computing Machinery, 2024. pp. 288–302.
DOI:10.1145/3658644.3690301
ISBN:979-8-4007-0636-3
Datei: 2309.12041
Johannes Liebenow, Yara Schütt, Tanya Braun, Marcel Gehrke, Florian Thaeter, and Esfandiar Mohammadi,
DPM: Clustering Sensitive Data through Separation, in Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security, CCS 2024 , ACM, 2024.
DOI:10.48550/arXiv.2307.02969
Datei: arXiv.2307.02969