Related papers: Analyzing Federated Learning through an Adversaria…
Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e.,…
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…
Federated learning (FL) allows distributed participants to train machine learning models in a decentralized manner. It can be used for radio signal classification with multiple receivers due to its benefits in terms of privacy and…
Advances in distributed machine learning can empower future communications and networking. The emergence of federated learning (FL) has provided an efficient framework for distributed machine learning, which, however, still faces many…
Federated Learning (FL) is a popular distributed machine learning paradigm that enables jointly training a global model without sharing clients' data. However, its repetitive server-client communication gives room for backdoor attacks with…
Federated Learning (FL) is a decentralized machine learning method that enables participants to collaboratively train a model without sharing their private data. Despite its privacy and scalability benefits, FL is susceptible to backdoor…
Federated learning performs distributed model training using local data hosted by agents. It shares only model parameter updates for iterative aggregation at the server. Although it is privacy-preserving by design, federated learning is…
Existing model poisoning attacks to federated learning assume that an attacker has access to a large fraction of compromised genuine clients. However, such assumption is not realistic in production federated learning systems that involve…
Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients upload manipulated updates to degrade the performance of the global model. Although detection methods can identify and remove malicious clients, the model…
Various attack methods against recommender systems have been proposed in the past years, and the security issues of recommender systems have drawn considerable attention. Traditional attacks attempt to make target items recommended to as…
An attack on deep learning systems where intelligent machines collaborate to solve problems could cause a node in the network to make a mistake on a critical judgment. At the same time, the security and privacy concerns of AI have…
Federated learning is a distributed framework designed to address privacy concerns. However, it introduces new attack surfaces, which are especially prone when data is non-Independently and Identically Distributed. Existing approaches fail…
We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…
Federated learning is used to train a shared model in a decentralized way without clients sharing private data with each other. Federated learning systems are susceptible to poisoning attacks when malicious clients send false updates to the…
Current defense mechanisms against model poisoning attacks in federated learning (FL) systems have proven effective up to a certain threshold of malicious clients. In this work, we introduce FLANDERS, a novel pre-aggregation filter for FL…
Federated machine learning which enables resource constrained node devices (e.g., mobile phones and IoT devices) to learn a shared model while keeping the training data local, can provide privacy, security and economic benefits by designing…
Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards…
We investigate a specific security risk in FL: a group of malicious clients has impacted the model during training by disguising their identities and acting as benign clients but later switching to an adversarial role. They use their data,…
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning attacks, the attacker reduces the model's performance on…
Federated learning is known to be vulnerable to both security and privacy issues. Existing research has focused either on preventing poisoning attacks from users or on concealing the local model updates from the server, but not both.…