Related papers: Defending Against Sophisticated Poisoning Attacks …
Federated learning enables training high-utility models across several clients without directly sharing their private data. As a downside, the federated setting makes the model vulnerable to various adversarial attacks in the presence of…
Federated Learning (FL) in 5G and edge network environments face severe security threats from adversarial clients. Malicious participants can perform label flipping, inject backdoor triggers, or launch Sybil attacks to corrupt the global…
Federated Learning (FL) remains highly vulnerable to poisoning attacks, especially under real-world hyper-heterogeneity, where clients differ significantly in data distributions, communication capabilities, and model architectures. Such…
Federated learning (FL) allows multiple clients to collaboratively train a global machine learning model through a server, without exchanging their private training data. However, the decentralized aspect of FL makes it susceptible to…
Federated learning combines local updates from clients to produce a global model, which is susceptible to poisoning attacks. Most previous defense strategies relied on vectors derived from projections of local updates on a Euclidean space;…
Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms…
This review paper takes a comprehensive look at malicious attacks against FL, categorizing them from new perspectives on attack origins and targets, and providing insights into their methodology and impact. In this survey, we focus on…
This paper proposes a novel, data-agnostic, model poisoning attack on Federated Learning (FL), by designing a new adversarial graph autoencoder (GAE)-based framework. The attack requires no knowledge of FL training data and achieves both…
The uneven distribution of local data across different edge devices (clients) results in slow model training and accuracy reduction in federated learning. Naive federated learning (FL) strategy and most alternative solutions attempted to…
Recent advancements in Deep Reinforcement Learning (DRL) have demonstrated its applicability across various domains, including robotics, healthcare, energy optimization, and autonomous driving. However, a critical question remains: How…
Federated learning is vulnerable to poisoning and backdoor attacks under partial observability. We formulate defence as a partially observable sequential decision problem and introduce a trust-aware Deep Q-Network that integrates…
Federated learning allows multiple clients to collaboratively train a global model with the assistance of a server. However, its distributed nature makes it susceptible to poisoning attacks, where malicious clients can compromise the global…
In federated learning (FL), although the original intention of available but not visible data is to allay data privacy concerns, it potentially brings new security threats, particularly poisoning attacks that target such not visible local…
Distributed learning paradigms, such as federated and decentralized learning, allow for the coordination of models across a collection of agents, and without the need to exchange raw data. Instead, agents compute model updates locally based…
Federated learning is a prominent framework that enables clients (e.g., mobile devices or organizations) to train a collaboratively global model under a central server's orchestration while keeping local training datasets' privacy. However,…
Availability poisons exploit supervised learning (SL) algorithms by introducing class-related shortcut features in images such that models trained on poisoned data are useless for real-world datasets. Self-supervised learning (SSL), which…
Decentralized Federated Learning (DFL), a paradigm for managing big data in a privacy-preserved manner, is still vulnerable to poisoning attacks where malicious clients tamper with data or models. Current defense methods often assume…
Federated Learning(FL), in theory, preserves privacy of individual clients' data while producing quality machine learning models. However, attacks such as Deep Leakage from Gradients(DLG) severely question the practicality of FL. In this…
Data-driven deep learning (DL) techniques developed for automatic modulation classification (AMC) of wireless signals are vulnerable to adversarial attacks. This poses a severe security threat to the DL-based wireless systems, specifically…
This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients' training data are not independent and identically distributed. We propose a heuristic algorithm…