Related papers: Adversarially Guided Stateful Defense Against Back…

In Federated Learning (FL), models are as fragile as centrally trained models against adversarial examples. However, the adversarial robustness of federated learning remains largely unexplored. This paper casts light on the challenge of…

Federated learning (FL) is revolutionizing how we learn from data. With its growing popularity, it is now being used in many safety-critical domains such as autonomous vehicles and healthcare. Since thousands of participants can contribute…

Deep Neural Networks (DNNs) are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model. Current backdoor defenses on poisoned data often suffer from high computational costs or low…

Federated Learning (FL) enables geographically distributed clients to collaboratively train machine learning models by sharing only their local models, ensuring data privacy. However, FL is vulnerable to untargeted attacks that aim to…

Deep learning achieves state-of-the-art performance in many tasks but exposes to the underlying vulnerability against adversarial examples. Across existing defense techniques, adversarial training with the projected gradient decent attack…

Federated Learning (FL) enables collaborative model training across multiple clients without sharing private data. We consider FL scenarios wherein FL clients are subject to adversarial (Byzantine) attacks, while the FL server is trusted…

Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private…

Federated Learning (FL) is a decentralized learning paradigm, enabling parties to collaboratively train models while keeping their data confidential. Within autonomous driving, it brings the potential of reducing data storage costs,…

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which…

The decentralized and privacy-preserving nature of federated learning (FL) makes it vulnerable to backdoor attacks aiming to manipulate the behavior of the resulting model on specific adversary-chosen inputs. However, most existing defenses…

Large models adaptation through Federated Learning (FL) addresses a wide range of use cases and is enabled by Parameter-Efficient Fine-Tuning techniques such as Low-Rank Adaptation (LoRA). However, this distributed learning paradigm faces…

Deep learning has shown incredible potential across a wide array of tasks, and accompanied by this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal…

Aiming at privacy preservation, Federated Learning (FL) is an emerging machine learning approach enabling model training on decentralized devices or data sources. The learning mechanism of FL relies on aggregating parameter updates from…

This paper proposes a generative adversarial network and federated learning-based model to address various challenges of the smart prediction and recommendation applications, such as high response time, compromised data privacy, and data…

Decentralized Federated Learning (DFL) emerges as an innovative paradigm to train collaborative models, addressing the single point of failure limitation. However, the security and trustworthiness of FL and DFL are compromised by poisoning…

Federated learning is a promising approach for training machine learning models while preserving data privacy. However, its distributed nature makes it vulnerable to backdoor attacks, particularly in NLP tasks, where related research…

Federated Learning enables entities to collaboratively learn a shared prediction model while keeping their training data locally. It prevents data collection and aggregation and, therefore, mitigates the associated privacy risks. However,…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Malicious clients can attack federated learning systems using malicious data, including backdoor samples, during the training phase. The compromised global model will perform well on the validation dataset designed for the task, but a small…

Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimately failing. We use a new metric to quantify the degree of…