[ICML 2022 / ICLR 2024] Source code for our papers "Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks" and "Be Careful What You Smooth For".

[IEEE S&P 22] "LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis" by Fan Wu, Yunhui Long, Ce Zhang, Bo Li

Code for "Variational Model Inversion Attacks" Wang et al., NeurIPS2021

The code and data for "Are Large Pre-Trained Language Models Leaking Your Personal Information?" (Findings of EMNLP '22)

Split Learning Simulation Framework for LLMs

Marich is a model-agnostic extraction algorithm. It uses a public data to query a private model, aggregates the predicted labels, and construct a distributionall equivalent/max-information leaking extracted model.

Source code for https://arxiv.org/abs/2301.10053

A mitigation method against privacy violation attacks on face recognition systems

[NeurIPS 2024] "Pseudo-Private Data Guided Model Inversion Attacks"