Yang Zhang

发表

Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning

Tribhuvanesh Orekondy, Seong Joon Oh, Yang Zhang, 2018 .

Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning

Seong Joon Oh, Mario Fritz, B. Schiele, 2018, 1805.05838.

GAN-Leaks: A Taxonomy of Membership Inference Attacks against GANs

Mario Fritz, Yang Zhang, Dingfan Chen, 2019, ArXiv.

Poster: Membership Inference Against DNA Methylation Databases: Attacks and Defenses

R. Eils, Yang Zhang, M. Backes, 2019 .

Dynamic Backdoor Attacks Against Machine Learning Models

Yang Zhang, M. Backes, Shiqing Ma, 2020, 2022 IEEE 7th European Symposium on Security and Privacy (EuroS&P).

Poster: Towards Plausible Graph Anonymization

Yang Zhang, Mathias Humbert, Jilles Vreeken, 2022 .

Gradient-Leaks: Understanding Deanonymization in Federated Learning

Tribhuvanesh Orekondy, Seong Joon Oh, Yang Zhang, 2019 .

MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples

N. Gong, Yang Zhang, M. Backes, 2019, CCS.

Fine-Tuning Is All You Need to Mitigate Backdoor Attacks

Yang Zhang, Mathias Humbert, Pascal Berrang, 2022, ArXiv.

Membership Inference Against DNA Methylation Databases

Michael Backes, Roland Eils, Yang Zhang, 2020, 2020 IEEE European Symposium on Security and Privacy (EuroS&P).

MBeacon: Privacy-Preserving Beacons for DNA Methylation Data

Yang Zhang, Michael Backes, Haixu Tang, 2019, NDSS.

PrivSyn: Differentially Private Data Synthesis pdf

Ninghui Li, Michael Backes, Shibo He, 2020, USENIX Security Symposium.

ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models pdf

Mario Fritz, Michael Backes, Yang Zhang, 2018, NDSS.

BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements

Michael Backes, Qingni Shen, Ahmed Salem, 2020, ACSAC.

BadNL: Backdoor Attacks Against NLP Models pdf

Michael Backes, Yang Zhang, Ahmed Salem, 2020, ArXiv.

Quantifying and Mitigating Privacy Risks of Contrastive Learning

Yang Zhang, Xinlei He, Yang Zhang, 2021, CCS.

Graph Unlearning

Yang Zhang, M. Backes, Mathias Humbert, 2021, CCS.

Fairwalk: Towards Fair Graph Embedding

Michael Backes, Yang Zhang, Tahleen A. Rahman, 2019, IJCAI.

GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models

Mario Fritz, Ning Yu, Yang Zhang, 2019, CCS.

BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models pdf

Michael Backes, Yang Zhang, Ahmed Salem, 2020, ArXiv.

Don't Trigger Me! A Triggerless Backdoor Attack Against Deep Neural Networks pdf

Michael Backes, Yang Zhang, Ahmed Salem, 2020, ArXiv.

ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models pdf

Emiliano De Cristofaro, Mario Fritz, Michael Backes, 2021, USENIX Security Symposium.

When Machine Unlearning Jeopardizes Privacy

Michael Backes, Tianhao Wang, Zhikun Zhang, 2020, CCS.

MLCapsule: Guarded Offline Deployment of Machine Learning as a Service pdf

Yang Zhang, Mario Fritz, Michael Backes, 2018, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

Node-Level Membership Inference Attacks Against Graph Neural Networks pdf

Michael Backes, Yang Zhang, Xinlei He, 2021, ArXiv.

Amplifying Membership Exposure via Data Poisoning

Cong Wang, Yang Zhang, Yun Shen, 2022, NeurIPS.

Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning

N. Gong, Yang Zhang, Xinlei He, 2022, ECCV.

Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning pdf

Yang Zou, Michael Backes, Yang Zhang, 2020, ArXiv.

Inference Attacks Against Graph Neural Networks pdf

Michael Backes, Zhikun Zhang, Min Chen, 2021, USENIX Security Symposium.

Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning pdf

Yang Zhang, Mario Fritz, Michael Backes, 2019, USENIX Security Symposium.

Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models

Yang Zhang, Cory Cornelius, Weilin Xu, 2022, ArXiv.

Tagvisor: A Privacy Advisor for Sharing Hashtags

Yang Zhang, Cheng-Te Li, Jun Pang, 2018, WWW.

Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning

Seong Joon Oh, Mario Fritz, B. Schiele, 2018, 1805.05838.

Get a Model! Model Hijacking Attack Against Machine Learning Models pdf

Michael Backes, Ahmed Salem, Yang Zhang, 2021, NDSS.

Stealing Links from Graph Neural Networks pdf

Michael Backes, Xinlei He, Neil Zhenqiang Gong, 2020, USENIX Security Symposium.

Towards Plausible Graph Anonymization

Yang Zhang, M. Backes, Mathias Humbert, 2017, NDSS.

CTRL+Z: Recovering Anonymized Social Graphs pdf

Yang Zhang, Michael Backes, Jilles Vreeken, 2017, ArXiv.

Model Stealing Attacks Against Inductive Graph Neural Networks pdf

Yang Zhang, Yun Shen, Yufei Han, 2021, 2022 IEEE Symposium on Security and Privacy (SP).

White-box Membership Inference Attacks against Diffusion Models

Yang Zhang, Tianhao Wang, Mengdi Huai, 2023, ArXiv.

Dissecting Privacy Risks in Biomedical Data

Yang Zhang, Roland Eils, Michael Backes, 2018, 2018 IEEE European Symposium on Security and Privacy (EuroS&P).

SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmark

Yang Zhang, Xiaohong Jiang, Yulong Shen, 2023, arXiv.org.

This paper is included in the Proceedings of the 30th USENIX Security Symposium.

Yang Zhang, M. Backes, J. Honorio, 2022 .

White-box Membership Inference Attacks against Diffusion Models

Yang Zhang, Tianhao Wang, Mengdi Huai, 2023, ArXiv.

DatingSec: Detecting Malicious Accounts in Dating Apps Using a Content-Based Attention Network

Qingyuan Gong, Xin Wang, Yang Zhang, 2021, IEEE Transactions on Dependable and Secure Computing.

GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models

Mario Fritz, Yang Zhang, Dingfan Chen, 2019, CCS.