paper-with-me

홈 › Papers

On the Privacy Risks of Cell-Based NAS Architectures

2022-09-04 · Hai Huang, Zhikun Zhang, Yun Shen, Michael Backes, Qi Li, Yang Zhang

Existing studies on neural architecture search (NAS) mainly focus on efficiently and effectively searching for network architectures with better performance. Little progress has been made to systematically understand if the NAS-searched architectures are robust to privacy attacks while abundant work has already shown that human-designed architectures are prone to privacy attacks. In this paper, we fill this gap and systematically measure the privacy risks of NAS architectures. Leveraging the insights from our measurement study, we further explore the cell patterns of cell-based NAS architectures and evaluate how the cell patterns affect the privacy risks of NAS-searched architectures. Through extensive experiments, we shed light on how to design robust NAS architectures against privacy attacks, and also offer a general methodology to understand the hidden correlation between the NAS-searched architectures and other privacy risks.

📄 PDF Abstract BibTeX arXiv:2209.01688

Code (1)

miraclehh/nas_privacy 공식 구현 pytorch

Tasks

Neural Architecture Search

Similar Papers 제목 키워드 기반

Decoupling Generalizability and Membership Privacy Risks in Neural Networks

2026-02-02 · Xingli Fang, Jung-Eun Kim arxiv

A deep learning model usually has to sacrifice some utilities when it acquires some other abilities or characteristics. Privacy preservation has such trade-off relationships with utilities. The loss disparity between var…

Publishing Neural Networks in Drug Discovery Might Compromise Training Data Privacy

2024-10-22 · Fabian P. Krüger, Johan Östman, Lewis Mervin, Igor V. Tetko 외

This study investigates the risks of exposing confidential chemical structures when machine learning models trained on these structures are made publicly available. We use membership inference attacks, a common method to…

Drug DiscoveryMolecular Property PredictionProperty Prediction

Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure

2025-12-18 · Lulu Xue, Shengshan Hu, Linqiang Qian, Peijin Guo 외 arxiv

Machine unlearning is a newly popularized technique for removing specific training data from a trained model, enabling it to comply with data deletion requests. While it protects the rights of users requesting unlearning…

When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning

2025-06-06 · Ruining Sun, Hongsheng Hu, Wei Luo, Zhaoxi Zhang 외

With the rapid advancement of deep learning technology, pre-trained encoder models have demonstrated exceptional feature extraction capabilities, playing a pivotal role in the research and application of deep learning. H…

Contrastive LearningInference AttackMembership Inference AttackSelf-Supervised Learning

Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning

2023-12-10 · Jianwei Li, Sheng Liu, Qi Lei

Language models trained via federated learning (FL) demonstrate impressive capabilities in handling complex tasks while protecting user privacy. Recent studies indicate that leveraging gradient information and prior know…

CoLAFederated LearningSST-2text-classification+1