Shanghao Shi (Virginia Tech), Ning Wang (University of South Florida), Yang Xiao (University of Kentucky), Chaoyu Zhang (Virginia Tech), Yi Shi (Virginia Tech), Y. Thomas Hou (Virginia Polytechnic Institute and State University), Wenjing Lou (Virginia Polytechnic Institute and State University)

Federated learning is known for its capability to safeguard the participants' data privacy. However, recently emerged model inversion attacks (MIAs) have shown that a malicious parameter server can reconstruct individual users' local data samples from model updates. The state-of-the-art attacks either rely on computation-intensive iterative optimization methods to reconstruct each input batch, making scaling difficult, or involve the malicious parameter server adding extra modules before the global model architecture, rendering the attacks too conspicuous and easily detectable.

To overcome these limitations, we propose Scale-MIA, a novel MIA capable of efficiently and accurately reconstructing local training samples from the aggregated model updates, even when the system is protected by a robust secure aggregation (SA) protocol. Scale-MIA utilizes the inner architecture of models and identifies the latent space as the critical layer for breaching privacy. Scale-MIA decomposes the complex reconstruction task into an innovative two-step process. The first step is to reconstruct the latent space representations (LSRs) from the aggregated model updates using a closed-form inversion mechanism, leveraging specially crafted linear layers. Then in the second step, the LSRs are fed into a fine-tuned generative decoder to reconstruct the whole input batch.

We implemented Scale-MIA on commonly used machine learning models and conducted comprehensive experiments across various settings. The results demonstrate that Scale-MIA achieves excellent performance on different datasets, exhibiting high reconstruction rates, accuracy, and attack efficiency on a larger scale compared to state-of-the-art MIAs. Our code is available at https://github.com/unknown123489/Scale-MIA.

View More Papers

The Skeleton Keys: A Large Scale Analysis of Credential...

Yizhe Shi (Fudan University), Zhemin Yang (Fudan University), Kangwei Zhong (Fudan University), Guangliang Yang (Fudan University), Yifan Yang (Fudan University), Xiaohan Zhang (Fudan University), Min Yang (Fudan University)

Read More

Defending Against Membership Inference Attacks on Iteratively Pruned Deep...

Jing Shang (Beijing Jiaotong University), Jian Wang (Beijing Jiaotong University), Kailun Wang (Beijing Jiaotong University), Jiqiang Liu (Beijing Jiaotong University), Nan Jiang (Beijing University of Technology), Md Armanuzzaman (Northeastern University), Ziming Zhao (Northeastern University)

Read More

Heimdall: Towards Risk-Aware Network Management Outsourcing

Yuejie Wang (Peking University), Qiutong Men (New York University), Yongting Chen (New York University Shanghai), Jiajin Liu (New York University Shanghai), Gengyu Chen (Carnegie Mellon University), Ying Zhang (Meta), Guyue Liu (Peking University), Vyas Sekar (Carnegie Mellon University)

Read More

Crosstalk-induced Side Channel Threats in Multi-Tenant NISQ Computers

Ruixuan Li (Choudhury), Chaithanya Naik Mude (University of Wisconsin-Madison), Sanjay Das (The University of Texas at Dallas), Preetham Chandra Tikkireddi (University of Wisconsin-Madison), Swamit Tannu (University of Wisconsin, Madison), Kanad Basu (University of Texas at Dallas)

Read More