paper-with-me

Papers

Vicious Classifiers: Assessing Inference-time Data Reconstruction Risk in Edge Computing

2022-12-08 · Mohammad Malekzadeh, Deniz Gunduz

Privacy-preserving inference in edge computing paradigms encourages the users of machine-learning services to locally run a model on their private input and only share the models outputs for a target task with the server. We study how a vicious server can reconstruct the input data by observing only the models outputs while keeping the target accuracy very close to that of a honest server by jointly training a target model (to run at users' side) and an attack model for data reconstruction (to secretly use at servers' side). We present a new measure to assess the inference-time reconstruction risk. Evaluations on six benchmark datasets show the model's input can be approximately reconstructed from the outputs of a single inference. We propose a primary defense mechanism to distinguish vicious versus honest classifiers at inference time. By studying such a risk associated with emerging ML services our work has implications for enhancing privacy in edge computing. We discuss open challenges and directions for future studies and release our code as a benchmark for the community at https://github.com/mmalekzadeh/vicious-classifiers .

📄 PDF Abstract BibTeX arXiv:2212.04223

Code (1)

mmalekzadeh/vicious-classifiers 공식 구현 pytorch

Tasks

Edge-computingPrivacy PreservingReconstruction Attack

Similar Papers 제목 키워드 기반

FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data

2022-11-17 · Tailin Zhou, Jun Zhang, Danny H. K. Tsang

Federated learning allows multiple clients to collaboratively train a model without exchanging their data, thus preserving data privacy. Unfortunately, it suffers significant performance degradation due to heterogeneous …

Classifier calibrationFederated LearningImage Classification

Dynamic fairness - Breaking vicious cycles in automatic decision making

2019-02-01 · Benjamin Paaßen, Astrid Bunge, Carolin Hainke, Leon Sindelar 외

In recent years, machine learning techniques have been increasingly applied in sensitive decision making processes, raising fairness concerns. Past research has shown that machine learning may reproduce and even exacerba…

BIG-bench Machine LearningDecision MakingFairness

Scalable Attack on Graph Data by Injecting Vicious Nodes

2020-04-22 · Jihong Wang, Minnan Luo, Fnu Suya, Jundong Li 외

Recent studies have shown that graph convolution networks (GCNs) are vulnerable to carefully designed attacks, which aim to cause misclassification of a specific node on the graph with unnoticeable perturbations. However…

FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning

2025-01-09 · Yanbing Zhou, Xiangmou Qu, Chenlong You, Jiyang Zhou 외

Prototype-based federated learning has emerged as a promising approach that shares lightweight prototypes to transfer knowledge among clients with data heterogeneity in a model-agnostic manner. However, existing methods …

Classifier calibrationContrastive LearningFederated LearningRepresentation Learning

Ransomware Detection and Classification using Machine Learning

2023-11-05 · Kavitha Kunku, ANK Zaman, Kaushik Roy

Vicious assaults, malware, and various ransomware pose a cybersecurity threat, causing considerable damage to computer structures, servers, and mobile and web apps across various industries and businesses. These safety c…

Classification