Client Side

Client-side security in federated learning is a critical research area focusing on mitigating vulnerabilities arising from malicious actors manipulating local models or data before uploading them to a central server. Current research emphasizes developing robust client-side defenses against poisoning attacks, which aim to corrupt the global model, and exploring the detectability of data-stealing attacks originating from either malicious clients or servers. These efforts are crucial for ensuring the integrity and privacy of federated learning systems, impacting the trustworthiness and widespread adoption of this powerful machine learning paradigm across various applications.

Papers

November 12, 2024

SCORE: Syntactic Code Representations for Static Script Malware Detection
Ecenaz Erdemir, Kyuhong Park, Michael J. Morais, Vianne R. Gao, Marion Marschalek, Yi Fan
Data Detection Performance Score Client Side Multi Purpose Malware

February 18, 2024

Poisoning Federated Recommender Systems with Fake Users
Ming Yin, Yichang Xu, Minghong Fang, Neil Zhenqiang Gong
Federated Learning Poisoning Attack Malicious Agent Federated Recommendation Fake User Client Side

July 18, 2023

FedDefender: Client-Side Attack-Tolerant Federated Learning
Sungwon Park, Sungwon Han, Fangzhao Wu, Sundong Kim, Bin Zhu, Xing Xie, Meeyoung Cha
Federated Learning Model Poisoning Attack Global Distillation Client Side

June 5, 2023

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
Kostadin Garov, Dimitar I. Dimitrov, Nikola Jovanović, Martin Vechev
Secure Aggregation Accurate Decoding Plain Sight Attack Framework Client Side

May 6, 2023

Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoning
Zijian Wang, Shuo Huang, Yujin Huang, Helei Cui
Device Deep Device Use Case Device Model Latency Attack Client Side Sponge Attack

March 31, 2023

A Generative Framework for Low-Cost Result Validation of Machine Learning-as-a-Service Inference
Abhinav Kumar, Miguel A. Guirao Aguilera, Reza Tourani, Satyajayant Misra
Generative Framework Efficient Verification Inference Service Integrity Verification Client Side

December 8, 2022

Re-purposing Perceptual Hashing based Client Side Scanning for Physical Surveillance
Ashish Hooda, Andrey Labunets, Tadayoshi Kohno, Earlence Fernandes
Robust Detection Physical Surveillance Client Side Perceptual Hashing

August 27, 2022

Network-Level Adversaries in Federated Learning
Giorgio Severi, Matthew Jagielski, Gökberk Yar, Yuxuan Wang, Alina Oprea, Cristina Nita-Rotaru
Attack Surface Client Side