相关论文: Attack of the Tails: Yes, You Really Can Backdoor …

Adversarial input image perturbation attacks have emerged as a significant threat to machine learning algorithms, particularly in image classification setting. These attacks involve subtle perturbations to input images that cause neural…

Federated learning (FL) refers to a distributed machine learning framework involving learning from several decentralized edge clients without sharing local dataset. This distributed strategy prevents data leakage and enables on-device…

Federated Learning (FL) enables training of a global model from distributed data, while preserving data privacy. However, the singular-model based operation of FL is open with uploading poisoned models compatible with the global model…

Federated learning enables learning from decentralized data sources without compromising privacy, which makes it a crucial technique. However, it is vulnerable to model poisoning attacks, where malicious clients interfere with the training…

Deep neural networks (DNNs) provide excellent performance across a wide range of classification tasks, but their training requires high computational resources and is often outsourced to third parties. Recent work has shown that outsourced…

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…

Recent advances in Federated Learning (FL) have brought large-scale collaborative machine learning opportunities for massively distributed clients with performance and data privacy guarantees. However, most current works focus on the…

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…

As a distributed collaborative machine learning paradigm, vertical federated learning (VFL) allows multiple passive parties with distinct features and one active party with labels to collaboratively train a model. Although it is known for…

Federated learning (FL) is a promising technique that enables a large amount of edge computing devices to collaboratively train a global learning model. Due to privacy concerns, the raw data on devices could not be available for centralized…

Federated Learning (FL) is a distributed machine learning approach that maintains data privacy by training on decentralized data sources. Similar to centralized machine learning, FL is also susceptible to backdoor attacks, where an attacker…

We introduce a formal notion of defendability against backdoors using a game between an attacker and a defender. In this game, the attacker modifies a function to behave differently on a particular input known as the "trigger", while…

Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server. However, the…

Federated Learning (FL) has emerged as a potentially powerful privacy-preserving machine learning methodology, since it avoids exchanging data between participants, but instead exchanges model parameters. FL has traditionally been applied…

Federated Learning (FL) is a machine learning paradigm in which many clients cooperatively train a single centralized model while keeping their data private and decentralized. FL is commonly used in edge computing, which involves placing…

Federated learning (FL) allows participants to jointly train a machine learning model without sharing their private data with others. However, FL is vulnerable to poisoning attacks such as backdoor attacks. Consequently, a variety of…

Federated Learning (FL) has received increasing attention due to its privacy protection capability. However, the base algorithm FedAvg is vulnerable when it suffers from so-called backdoor attacks. Former researchers proposed several robust…

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…

Recent studies have shown that contrastive learning, like supervised learning, is highly vulnerable to backdoor attacks wherein malicious functions are injected into target models, only to be activated by specific triggers. However, thus…

Federated learning (FL) is an appealing paradigm that allows a group of machines (a.k.a. clients) to learn collectively while keeping their data local. However, due to the heterogeneity between the clients' data distributions, the model…