لطفا منتظر بمانید ...
0% Complete
English
صفحه اصلی
/
شانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
FedCloak: Backdoor-Based Covert Channels in Federated Learning
نویسندگان :
Mohammad Matin Rezaeifard
1
Fatemeh Zahedi
2
Seyed Arsalan Vasegh Rahim Parvar
3
Reza Ebrahimi Atani
4
1- دانشگاه گیلان
2- دانشگاه گیلان
3- دانشگاه گیلان
4- دانشگاه گیلان
کلمات کلیدی :
Federated learning،Backdoor Attacks،Covert communication،Data Poisoning،Binary Memoryless Channel (BMC)،Adversarial Machine Learning،Model Aggregation،Security and privacy in distributed systems
چکیده :
Federated learning enables collaborative model training without centralizing data, but its distributed structure also exposes new vectors for covert communication. Existing schemes that embed messages in model parameters often require fine grained control and support only single sender settings, limiting their practicality. This paper introduces FedCloak, a novel framework that transforms data poisoning backdoor attacks into multi party covert channels within federated learning systems. By encoding bits through the global model’s transition between clean and triggered states, FedCloak allows colluding clients to exchange information without modifying aggregation protocols or model internals. The communication process is analytically modeled as a binary memoryless channel, enabling quantitative estimation of reliability via bit prediction accuracy. Experiments on CIFAR-10 with ResNet-9 across four aggregation algorithms (FedAvg, Trimmed Mean, Krum, and Multi-Krum) show that FedCloak achieves stable, high accuracy transmission even under aggregation noise. These results demonstrate that backdoor dynamics can act as an effective and practical substrate for covert communication in federated learning.
لیست مقالات
لیست مقالات بایگانی شده
A Survey on Utilizing Reinforcement Learning in Wireless Sensor Networks Routing Protocols
Ali Forghani Elah Abadi - Seyedeh Elham Asghari - Sepideh Sharifani - Seyyed Amir Asghari - Mohammadreza Binesh Marvasti
Stock Market Prediction Using Hard and Soft Data Fusion
Saeed Mohammadi Dashtaki - Masoud Alizadeh - Behzad Moshiri
تشخیص بیماری مزمن کلیوی با استفاده از یادگیرندههای گروهی و انتخاب ویژگیهای مؤثر مبتنی بر الگوریتم بهینهسازی تبادل حرارتی
صبا عارفنیا - مهدی هاشمزاده - امین گلزاری اسکوئی
Cryptanalysis of two password authenticated key exchange schemes
Mohammad Ali Poorafsahi - Hamid Mala
Movable Antenna Design for UAV-Aided Federated Learning via Deep Reinforcement Learning
MOHSEN Ahmadzadeh - Saeid Pakravan - Ghosheh Abed Hodtani
Robustness Gap in NLP Models for Vulnerability Descriptions: Benchmarking and Data Augmentation
AmirHossein Majd - Mahdi Yousefikia - Saghar Ghasemzadeh - Amirreza Asari - Arya Khoshnavataher - Seyedeh Leili Mirtaheri
بررسی امنیت وفقی در اینترنت وسایل نقلیه
سیده یگانه غیور باغبانی - دکتر سعید جلیلی سیده یگانه غیور باغبانی - سعید جلیلی -
Optimal control of robotic hand for rehabilitation using fractional order systems and EEG signal processing
Mehran Safari Dehnavi - Vahid Safari Dehnavi - Masoud Shafiee
Knowledge Distillation through a Knowledge Representation Approach (Knowledge Engineering)
Mohammad Hadi Safari Nader
A Potential Solutions-Based Parallelized GA for Application Graph Mapping in Reconfigurable Hardware
Seyed Mehdi Mohtavipour - Hadi Shahriar Shahhoseini
بیشتر
ثمین همایش، سامانه مدیریت همایش ها و جشنواره ها - نگارش 45.0.1