paper-with-me

Papers

Rethinking Model Inversion Attacks With Patch-Wise Reconstruction

2023-12-12 · Jonggyu Jang, Hyeonsu Lyu, Hyun Jong Yang

Model inversion (MI) attacks aim to infer or reconstruct the training dataset through reverse-engineering from the target model's weights. Recently, significant advancements in generative models have enabled MI attacks to overcome challenges in producing photo-realistic replicas of the training dataset, a technique known as generative MI. The generative MI primarily focuses on identifying latent vectors that correspond to specific target labels, leveraging a generative model trained with an auxiliary dataset. However, an important aspect is often overlooked: the MI attacks fail if the pre-trained generative model lacks the coverage to create an image corresponding to the target label, especially when there is a significant difference between the target and auxiliary datasets. To address this gap, we propose the Patch-MI method, inspired by a jigsaw puzzle, which offers a novel probabilistic interpretation of MI attacks. Even with a dissimilar auxiliary dataset, our method effectively creates images that closely mimic the distribution of image patches in the target dataset by patch-based reconstruction. Moreover, we numerically demonstrate that the Patch-MI improves Top 1 attack accuracy by 5\%p compared to existing methods.

📄 PDF Abstract BibTeX arXiv:2312.07040

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial Network

Methods 이 논문이 사용한 방법론

Jigsaw Jigsaw is a self-supervision approach that relies on jigsaw-like puzzles as the pretext task in order to learn image representations.

Similar Papers 제목 키워드 기반

Rethinking Generative Reconstruction Attacks against Graph Neural Network Models

2026-06-29 · Adebayo Keji, Sayanton Dibbo arxiv

The application of graph data in numerous disciplines raises the need for gathering and analyzing huge volumes of data, some of which is private and sensitive. The non-Euclidean nature of the graph data makes the analysi…

Graph Neural Network

Compressive Sensing via Low-Rank Gaussian Mixture Models

2015-08-27 · Xin Yuan, Hong Jiang, Gang Huang, Paul A. Wilford

We develop a new compressive sensing (CS) inversion algorithm by utilizing the Gaussian mixture model (GMM). While the compressive sensing is performed globally on the entire image as implemented in our lensless camera, …

Compressive Sensing

Practical Feasibility of Gradient Inversion Attacks in Federated Learning

2025-08-27 · Viktor Valadi, Mattias Åkesson, Johan Östman, Fazeleh Hoseini 외 arxiv

Gradient inversion attacks are often presented as a serious privacy threat in federated learning, with recent work reporting increasingly strong reconstructions under favorable experimental settings. However, it remains …

Image ReconstructionImage ClassificationFederated LearningObject Detection

Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks

2022-03-01 · Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis

Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reve…

Federated Learning

Exploring User-level Gradient Inversion with a Diffusion Prior

2024-09-11 · Zhuohang Li, Andrew Lowy, Jing Liu, Toshiaki Koike-Akino 외

We explore user-level gradient inversion as a new attack surface in distributed learning. We first investigate existing attacks on their ability to make inferences about private information beyond training data reconstru…

Denoising