Decaf: Data Distribution Decompose Attack against Federated Learning

no code implementations • 24 May 2024 • Zhiyang Dai, Chunyi Zhou, Anmin Fu

This attack enables an honest-but-curious FL server to meticulously profile the proportion of each class owned by the victim FL user, divulging sensitive information like local market item distribution and business competitiveness.

Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects

no code implementations • 13 Mar 2024 • Na Li, Chunyi Zhou, Yansong Gao, Hui Chen, Anmin Fu, Zhi Zhang, Yu Shui

Data users have been endowed with the right to be forgotten of their data.

Machine Unlearning

PPA: Preference Profiling Attack Against Federated Learning

no code implementations • 10 Feb 2022 • Chunyi Zhou, Yansong Gao, Anmin Fu, Kai Chen, Zhiyang Dai, Zhi Zhang, Minhui Xue, Yuqing Zhang

By observing a user model's gradient sensitivity to a class, PPA can profile the sample proportion of the class in the user's local dataset, and thus the user's preference of the class is exposed.

Federated Learning Inference Attack