Adam Dziedzic

Helmholtz Center for Information Security — Germany

Computer Science · Physical Sciences

17h-index890citations81works1.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Privacy-Preserving Technologies in Data(18), Adversarial Robustness in Machine Learning(12), Anomaly Detection Techniques and Applications(9), Advanced Database Systems and Queries(7), Neural Networks and Applications(5)

Publications81 total

Unlocking Post-hoc Dataset Inference with Synthetic Data
CISPA Helmholtz Center·2026Open Access
Unlocking Post-hoc Dataset Inference with Synthetic Data
CISPA Helmholtz Center·2026Open Access
Secure Noise Sampling for Differentially Private Collaborative Learning
2025· 1 citedOpen Access
On Stealing Graph Neural Network Models
arXiv (Cornell University)·2025Open Access
Localizing and Mitigating Memorization in Image Autoregressive Models
arXiv (Cornell University)·2025Open Access
Demystifying Foreground-Background Memorization in Diffusion Models
arXiv (Cornell University)·2025Open Access
Finding Dori: Memorization in Text-to-Image Diffusion Models Is Not Local
arXiv (Cornell University)·2025Open Access
Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models
arXiv (Cornell University)·2025Open Access
BitMark: Watermarking Bitwise Autoregressive Image Generative Models
arXiv (Cornell University)·2025Open Access
Unlocking Post-hoc Dataset Inference with Synthetic Data
arXiv (Cornell University)·2025Open Access
CDI: Copyrighted Data Identification in Diffusion Models
2025
Exploring the limits of strong membership inference attacks on large language models
ArXiv.org·2025Open Access
Differentially Private Prototypes for Imbalanced Transfer Learning
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 1 citedOpen Access
DP-GPL: Differentially Private Graph Prompt Learning
arXiv (Cornell University)·2025Open Access
ADAGE: Active Defenses Against GNN Extraction
arXiv (Cornell University)·2025Open Access
Differentially Private Federated Learning With Time-Adaptive Privacy Spending
arXiv (Cornell University)·2025Open Access
Precise Parameter Localization for Textual Generation in Diffusion Models
ArXiv.org·2025Open Access
Captured by Captions: On Memorization and its Mitigation in CLIP Models
arXiv (Cornell University)·2025Open Access
Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images
arXiv (Cornell University)·2025Open Access
Privacy Attacks on Image AutoRegressive Models
arXiv (Cornell University)·2025Open Access
page 1 of 5Next →

Frequent Co-authors

Nicolas Papernot(20), Franziska Boenisch(17), Aaron J. Elmore(8), Sanjay Krishnan(8), Muhammad Ahmad Kaleem(6), Somesh Jha(5), Ali Shahin Shamsabadi(4), Tim Mattson(4), Vijay Gadepally(4), Zuohao She(4), Michael Stonebraker(4), Christopher A. Choquette-Choo(4), Michael Backes(4), Roei Schuster(3), Ilia Shumailov(3), Kyle O’Brien(3), Jeremy Kepner(3), Samuel Madden(3), Congyu Fang(3), Natalie Dullerud(3)