From Curvature to Privacy: EER-Driven Differential Privacy in Deep Neural Networks

Islam Monir; Gabriel Ghinita; Mohamed Abdallah

doi:10.1145/3779208.3805970

From Curvature to Privacy: EER-Driven Differential Privacy in Deep Neural Networks

Islam Monir
, Gabriel Ghinita
, Mohamed Abdallah

Computer Science

Hamad bin Khalifa University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Original language	English
Title of host publication	ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security
Publisher	Association for Computing Machinery, Inc
Pages	1770-1785
Number of pages	16
ISBN (Electronic)	9798400723568
DOIs	https://doi.org/10.1145/3779208.3805970
State	Published - Jun 4 2026
Event	21st ACM Asia Conference on Computer and Communications Security, AsiaCCS 2026 - Bangalore, India Duration: Jun 1 2026 → Jun 5 2026

Publication series

Name	ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security

Conference

Conference	21st ACM Asia Conference on Computer and Communications Security, AsiaCCS 2026
Country/Territory	India
City	Bangalore
Period	6/1/26 → 6/5/26

ASJC Scopus Subject Areas

Computational Theory and Mathematics
Computer Networks and Communications
Computer Science Applications

Keywords

Differential Privacy
Empirical Risk Minimization
Expected Excess Risk
Machine Learning
Neural Networks

Access to Document

10.1145/3779208.3805970

Cite this

Monir, I., Ghinita, G., & Abdallah, M. (2026). From Curvature to Privacy: EER-Driven Differential Privacy in Deep Neural Networks. In ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security (pp. 1770-1785). (ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security). Association for Computing Machinery, Inc. https://doi.org/10.1145/3779208.3805970

From Curvature to Privacy: EER-Driven Differential Privacy in Deep Neural Networks. / Monir, Islam; Ghinita, Gabriel; Abdallah, Mohamed.
ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security. Association for Computing Machinery, Inc, 2026. p. 1770-1785 (ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Monir, I, Ghinita, G & Abdallah, M 2026, From Curvature to Privacy: EER-Driven Differential Privacy in Deep Neural Networks. in ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security. ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security, Association for Computing Machinery, Inc, pp. 1770-1785, 21st ACM Asia Conference on Computer and Communications Security, AsiaCCS 2026, Bangalore, India, 6/1/26. https://doi.org/10.1145/3779208.3805970

Monir I, Ghinita G, Abdallah M. From Curvature to Privacy: EER-Driven Differential Privacy in Deep Neural Networks. In ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security. Association for Computing Machinery, Inc. 2026. p. 1770-1785. (ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security). doi: 10.1145/3779208.3805970

Monir, Islam ; Ghinita, Gabriel ; Abdallah, Mohamed. / From Curvature to Privacy : EER-Driven Differential Privacy in Deep Neural Networks. ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security. Association for Computing Machinery, Inc, 2026. pp. 1770-1785 (ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security).

@inproceedings{6836e11d64b449ae8b8063c4492b6828,

title = "From Curvature to Privacy: EER-Driven Differential Privacy in Deep Neural Networks",

keywords = "Differential Privacy, Empirical Risk Minimization, Expected Excess Risk, Machine Learning, Neural Networks",

author = "Islam Monir and Gabriel Ghinita and Mohamed Abdallah",

note = "Publisher Copyright: {\textcopyright} 2026 Copyright held by the owner/author(s).; 21st ACM Asia Conference on Computer and Communications Security, AsiaCCS 2026 ; Conference date: 01-06-2026 Through 05-06-2026",

year = "2026",

month = jun,

day = "4",

doi = "10.1145/3779208.3805970",

language = "English",

series = "ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security",

publisher = "Association for Computing Machinery, Inc",

pages = "1770--1785",

booktitle = "ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security",

}

TY - GEN

T1 - From Curvature to Privacy

T2 - 21st ACM Asia Conference on Computer and Communications Security, AsiaCCS 2026

AU - Monir, Islam

AU - Ghinita, Gabriel

AU - Abdallah, Mohamed

PY - 2026/6/4

Y1 - 2026/6/4

KW - Differential Privacy

KW - Empirical Risk Minimization

KW - Expected Excess Risk

KW - Machine Learning

KW - Neural Networks

UR - https://www.scopus.com/pages/publications/105042492368

UR - https://www.scopus.com/pages/publications/105042492368#tab=citedBy

U2 - 10.1145/3779208.3805970

DO - 10.1145/3779208.3805970

M3 - Conference contribution

AN - SCOPUS:105042492368

T3 - ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security

SP - 1770

EP - 1785

BT - ASIA CCS 2026 - Proceedings of the 21st ACM ASIA Conference on Computer and Communications Security

PB - Association for Computing Machinery, Inc

Y2 - 1 June 2026 through 5 June 2026

ER -

From Curvature to Privacy: EER-Driven Differential Privacy in Deep Neural Networks

Publication series

Conference

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this