Send email Copy Email Address
Research Group

Yang Zhang

Machine Learning and Data Privacy

Our group conducts research in the intersection of machine learning and data privacy. On the one hand, we use machine learning models to assess and mitigate the privacy risks stemming from various kinds of data, such as social network data and biomedical data. On the other hand, we investigate the privacy risks of machine learning models.

Head of Group

Yang Zhang

Email

Address

Im Oberen Werk 1
66386 St. Ingbert (Germany)

Members

Placeholder

Boyang Zhang

Zheng Li
Placeholder

Zeyang Sha

Yukun Jiang
Placeholder

Xun Wang
Placeholder

Yicong Tan
Placeholder

Chi Cui

Most Recent Publications

Year 2024

2024-11-12

ModScan: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities

Conference / Medium

Conference on Empirical Methods in Natural Language Processing (EMNLP)

Tags
Trustworthy Information Processing
Authors
Visit Detail Page
2024-11-12

The Death and Life of Great Prompts: Analyzing the Evolution of LLM Prompts from the Structural Perspective

Conference / Medium

Conference on Empirical Methods in Natural Language Processing (EMNLP)

Tags
Trustworthy Information Processing
Authors
Visit Detail Page
2024-10-19

Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders

Conference / Medium

European Conference on Artificial Intelligence (ECAI)

Tags
Trustworthy Information Processing
Authors
Full Paper Visit Detail Page
2024-10-14

Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution

Conference / Medium

ACM Conference on Computer and Communications Security (CCS)

Tags
Trustworthy Information Processing
Authors
Visit Detail Page
2024-10-14

Membership Inference Attacks Against In-Context Learning

Conference / Medium

ACM Conference on Computer and Communications Security (CCS)

Tags
Trustworthy Information Processing
Authors
Visit Detail Page