[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
The code and data for "Are Large Pre-Trained Language Models Leaking Your Personal Information?" (Findings of EMNLP '22)
Code for "Variational Model Inversion Attacks" Wang et al., NeurIPS2021
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
[NeurIPS 2024] "Pseudo-Private Data Guided Model Inversion Attacks"
A mitigation method against privacy violation attacks on face recognition systems
Add a description, image, and links to the privacy-attacks topic page so that developers can more easily learn about it.
To associate your repository with the privacy-attacks topic, visit your repo's landing page and select "manage topics."