Send email Copy Email Address
Faculty

Adam Dziedzic

Research Group
Trustworthy Information Processing

Email

Phone

Address

Im Oberen Werk 1
66386 St. Ingbert (Germany)

Further Information

Publications by Adam Dziedzic

Year 2024

2024-10-16

Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks

Conference / Medium

European Conference on Artificial Intelligence (ECAI)

Tags
Trustworthy Information Processing
Authors
Full Paper Visit Detail Page
2024-05-11

Memorization in Self-Supervised Learning Improves Downstream Generalization

Conference / Medium

International Conference on Learning Representations (ICLR)

Tags
Trustworthy Information Processing
Authors
Full Paper Visit Detail Page
2024-03-01

Decentralised, Collaborative, and Privacy-preserving Machine Learning for Multi-Hospital Data

Article

eBioMedicine

Tags
Trustworthy Information Processing
Authors
  • Congyu Fang
  • Adam Dziedzic
  • Lin Zhang
  • Laura Oliva
  • Amol Verma
  • Fahad Razak
  • Nicolas Papernot
  • Bo Wang
Full Paper Visit Detail Page
2024

Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS)

Tags
Authors
Visit Detail Page
2024

Localizing Memorization in SSL Vision Encoders

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS)

Tags
Trustworthy Information Processing
Authors
Visit Detail Page
2024

Open LLMs are Necessary for Private Adaptations and Outperform their Closed Alternatives

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS)

Tags
Trustworthy Information Processing
Authors
Visit Detail Page

Year 2023

2023-12-12

Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS)

Tags
Trustworthy Information Processing
Authors
Full Paper Visit Detail Page
2023-10-12

Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders.

Article

CoRR

Tags
Trustworthy Information Processing
Authors
Visit Detail Page
2023-09-23

Evaluating Robustness to Unforeseen Adversarial Attacks

Article

ICLR

Tags
Trustworthy Information Processing
Authors
Full Paper Visit Detail Page
2023-07-10

Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees.

Conference / Medium

Privacy Enhancing Technologies Symposium (PETS)

Tags
Trustworthy Information Processing
Authors
Visit Detail Page