Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jakub Breier

Jakub Breier

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Crypto×3AI×3ML×1

Frequent co-authors

Xiaolu Hou3×
Andrii Tyvodar1×
Andreas Rechberger1×
Dirmanto Jap1×
Shivam Bhasin1×
Bernhard Jungk1×

Research Timeline

2026
Beyond TVLA: Anderson-Darling Leakage Assessment for Neural Network Side-Channel Leakage Detection

This paper introduces Anderson-Darling Leakage Assessment (ADLA), a superior side-channel leakage detection method that tests full distributional differences, showing improved sensitivity over the standard TVLA, especially in protected neural network implementations.

A Constant-Time Implementation Methodology for Activation Functions on Microcontrollers

The paper proposes a constant-time implementation methodology for activation functions on microcontrollers to prevent timing side-channel attacks during embedded neural-network inference.

Characterizing the Fault Response of the Intel Neural Compute Stick 2 Under Single-Pulse Electromagnetic Fault Injection

The paper systematically characterizes the fault response of the Intel NCS2 accelerator to electromagnetic fault injection, revealing a major degradation mode that is undetectable by standard inference-API-level integrity checks.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 21, 2026

A Constant-Time Implementation Methodology for Activation Functions on Microcontrollers

Andrii Tyvodar, Andreas Rechberger, Dirmanto Jap, Shivam Bhasin +3 more

The paper proposes a constant-time implementation methodology for activation functions on microcontrollers to prevent timing side-channel attacks during embedded neural-network inference.

View →
cs.CRcs.AIcs.LGRecentMay 21, 2026

Characterizing the Fault Response of the Intel Neural Compute Stick 2 Under Single-Pulse Electromagnetic Fault Injection

Štefan Kučerák, Jakub Breier, Xiaolu Hou

The paper systematically characterizes the fault response of the Intel NCS2 accelerator to electromagnetic fault injection, revealing a major degradation mode that is undetectable by standard inferenc…

View →
cs.CRcs.AIRecentMar 19, 2026

Beyond TVLA: Anderson-Darling Leakage Assessment for Neural Network Side-Channel Leakage Detection

Ján Mikulec, Jakub Breier, Xiaolu Hou

This paper introduces Anderson-Darling Leakage Assessment (ADLA), a superior side-channel leakage detection method that tests full distributional differences, showing improved sensitivity over the sta…

View →