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

Marten van Dijk

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×2Crypto×2AI×1

Frequent co-authors

Murat Bilgehan Ertan2×
Xiaochen Zhu1×
Phuong Ha Nguyen1×
Srinivas Devadas1×

Research Timeline

2026
PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization

The paper introduces PACZero, a novel PAC-private fine-tuning mechanism that achieves usable utility for large language models while providing strong resistance against membership-inference attacks.

Trade-off Functions for DP-SGD with Subsampling based on Random Shuffling: Tight Upper and Lower Bounds

The paper provides a tight, transparent, and closed-form analysis of the trade-off function for Differentially Private SGD using random shuffling, significantly improving upon previous methods and establishing new asymptotic limits.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.CRRecentMay 7, 2026

PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization

Murat Bilgehan Ertan, Xiaochen Zhu, Phuong Ha Nguyen, Marten van Dijk +1 more

The paper introduces PACZero, a novel PAC-private fine-tuning mechanism that achieves usable utility for large language models while providing strong resistance against membership-inference attacks.

View →
cs.LGcs.CRRecentMay 7, 2026

Trade-off Functions for DP-SGD with Subsampling based on Random Shuffling: Tight Upper and Lower Bounds

Marten van Dijk, Murat Bilgehan Ertan

The paper provides a tight, transparent, and closed-form analysis of the trade-off function for Differentially Private SGD using random shuffling, significantly improving upon previous methods and est…

View →