paper-with-me

Papers

Knowledge-Enriched Distributional Model Inversion Attacks

2020-10-08 · ICCV 2021 10 · Si Chen, Mostafa Kahla, Ruoxi Jia, Guo-Jun Qi

Model inversion (MI) attacks are aimed at reconstructing training data from model parameters. Such attacks have triggered increasing concerns about privacy, especially given a growing number of online model repositories. However, existing MI attacks against deep neural networks (DNNs) have large room for performance improvement. We present a novel inversion-specific GAN that can better distill knowledge useful for performing attacks on private models from public data. In particular, we train the discriminator to differentiate not only the real and fake samples but the soft-labels provided by the target model. Moreover, unlike previous work that directly searches for a single data point to represent a target class, we propose to model a private data distribution for each target class. Our experiments show that the combination of these techniques can significantly boost the success rate of the state-of-the-art MI attacks by 150%, and generalize better to a variety of datasets and models. Our code is available at https://github.com/SCccc21/Knowledge-Enriched-DMI.

📄 PDF Abstract BibTeX arXiv:2010.04092

Code (2)

SCccc21/Knowledge-Enriched-Distributional-Model-Inversion-Attacks 공식 구현 pytorch
scccc21/knowledge-enriched-dmi 공식 구현 pytorch

Tasks

model

Similar Papers 제목 키워드 기반

Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks

2022-01-28 · Lukas Struppek, Dominik Hintersdorf, Antonio De Almeida Correia, Antonia Adler 외

Model inversion attacks (MIAs) aim to create synthetic images that reflect the class-wise characteristics from a target classifier's private training data by exploiting the model's learned knowledge. Previous research ha…

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

2019-11-17 · CVPR 2020 6 · Yuheng Zhang, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang 외

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that traini…

Face Recognitionregression

GI-SMN: Gradient Inversion Attack against Federated Learning without Prior Knowledge

2024-05-06 · Jin Qian, Kaimin Wei, Yongdong Wu, Jilian Zhang 외

Federated learning (FL) has emerged as a privacy-preserving machine learning approach where multiple parties share gradient information rather than original user data. Recent work has demonstrated that gradient inversion…

Federated LearningPrivacy Preserving

Text Embedding Inversion Security for Multilingual Language Models

2024-01-22 · Yiyi Chen, Heather Lent, Johannes Bjerva

Textual data is often represented as real-numbered embeddings in NLP, particularly with the popularity of large language models (LLMs) and Embeddings as a Service (EaaS). However, storing sensitive information as embeddi…

Reinforcement Learning-Based Black-Box Model Inversion Attacks

2023-04-10 · CVPR 2023 1 · Gyojin Han, Jaehyun Choi, Haeil Lee, Junmo Kim

Model inversion attacks are a type of privacy attack that reconstructs private data used to train a machine learning model, solely by accessing the model. Recently, white-box model inversion attacks leveraging Generative…

modelPrivacy Preservingreinforcement-learningReinforcement Learning