Model Poisoning Defense on Federated Learning: A Validation Based Approach

Wang, Yuao; Zhu, Tianqing; Chang, Wen-Han; Shen, Sheng; Ren, Wei

doi:10.1007/978-3-030-65745-1_12

Cited by 10 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can divide methods for detecting poisoning attacks based on evaluating model performance into two categories: evaluating local models [55], [57], [59], [62] and evaluating global models [56], [60], [63].…”

Section: ) Performance Evaluationmentioning

confidence: 99%

“…For example, Minghong et al [55] removed the local model that significantly negatively impacts the accuracy and loss of the global model. Yuao et al [57] updated the global model using only the local model that performed well on the test set and marked the client that uploaded a low-accuracy model as a malicious client. Furthermore, Mallah et al [59] defend the poisoning attack by monitoring: 1) the convergence of the local model during training, 2) the angular distance of successive local model updates, and 3) removing local model updates from clients whose performance does not improve to defend against poisoning attacks.…”

Section: ) Performance Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Poisoning Attacks in Federated Learning: A Survey

Xia

Chen

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Federated learning faces many security and privacy issues. Among them, poisoning attacks can significantly impact global models, and malicious attackers can prevent global models from converging or even manipulating the prediction results of global models. Defending against poisoning attacks is a very urgent and challenging task. However, the systematic reviews of poisoning attacks and their corresponding defense strategies from a privacy-preserving perspective still need more effort. This survey provides an in-depth and up-to-date overview of poisoning attacks and corresponding defense strategies in federated learning. We first classify the poisoning attacks according to their methods and targets. Next, we analyze the differences and connections between the various categories of poisoning attacks. In addition, we classify the defense strategies against poisoning attacks in federated learning into three categories and analyze their advantages and disadvantages. Finally, we discuss the privacy protection problem in poisoning attacks and their countermeasure and propose potential research directions from the perspective of attack and defense, respectively.INDEX TERMS Federated learning, distributed machine learning, poisoning attacks, defense of poisoning attacks.

show abstract

Section: ) Performance Evaluationmentioning

confidence: 99%

Section: ) Performance Evaluationmentioning

confidence: 99%

Poisoning Attacks in Federated Learning: A Survey

Xia

Chen

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Our proposed Performance Weighting scheme builds upon the work of Stripelis & Ambite (2020). Similar approaches were investigated by ; Wang et al (2020b). Specifically, in the authors aggregate the local models into sub-models and delegate their evaluation to learners that have a similar data distribution with the aggregated model, while in Wang et al (2020b) the authors evaluate the local models against a validation dataset that is hosted at the central server.…”

Section: Background and Related Workmentioning

confidence: 99%

“…Similar approaches were investigated by ; Wang et al (2020b). Specifically, in the authors aggregate the local models into sub-models and delegate their evaluation to learners that have a similar data distribution with the aggregated model, while in Wang et al (2020b) the authors evaluate the local models against a validation dataset that is hosted at the central server. However, both proposed approaches used the validation-based accuracy as a detection mechanism to discard corrupted learners from the federation, whereas in our work we keep the corrupted models in the federation with a downgraded contribution value.…”

Section: Background and Related Workmentioning

confidence: 99%

Performance Weighting for Robust Federated Learning Against Corrupted Sources

Stripelis¹,

Abram²,

Ambite³

2022

Preprint

View full text Add to dashboard Cite

Federated Learning has emerged as a dominant computational paradigm for distributed machine learning. Its unique data privacy properties allow us to collaboratively train models while offering participating clients certain privacy-preserving guarantees. However, in real-world applications, a federated environment may consist of a mixture of benevolent and malicious clients, with the latter aiming to corrupt and degrade federated model's performance. Different corruption schemes may be applied such as model poisoning and data corruption. Here, we focus on the latter, the susceptibility of federated learning to various data corruption attacks. We show that the standard global aggregation scheme of local weights is inefficient in the presence of corrupted clients. To mitigate this problem, we propose a class of task-oriented performance-based methods computed over a distributed validation dataset with the goal to detect and mitigate corrupted clients. Specifically, we construct a robust weight aggregation scheme based on geometric mean and demonstrate its effectiveness under random label shuffling and targeted label flipping attacks.

show abstract

“…Therefore, reducing the adversarial relevance on the global model. Other confidence or score-based anomaly detection have been proposed [77], [129], [130].…”

Section: B Defending Integrity and Availabilitymentioning

confidence: 99%

On the Security & Privacy in Federated Learning

Abad¹,

Picek²,

Ramírez-Durán³

et al. 2021

Preprint

View full text Add to dashboard Cite

Advances in Machine Learning (ML) and its wide range of applications boosted its popularity. Recent privacy awareness initiatives as the EU General Data Protection Regulation (GDPR) -European Parliament and Council Regulation No 2016/679, subdued ML to privacy and security assessments. Federated Learning (FL) grants a privacy-driven, decentralized training scheme that improves ML models' security. The industry's fast-growing adaptation and security evaluations of FL technology exposed various vulnerabilities. Depending on the FL phase, i.e., training or inference, the adversarial actor capabilities, and the attack type threaten FL's confidentiality, integrity, or availability (CIA). Therefore, the researchers apply the knowledge from distinct domains as countermeasures, like cryptography and statistics.This work assesses the CIA of FL by reviewing the state-of-theart (SoTA) for creating a threat model that embraces the attack's surface, adversarial actors, capabilities, and goals. We propose the first unifying taxonomy for attacks and defenses by applying this model. Additionally, we provide critical insights extracted by applying the suggested novel taxonomies to the SoTA, yielding promising future research directions.

show abstract

Model Poisoning Defense on Federated Learning: A Validation Based Approach

Cited by 10 publications

References 5 publications

Poisoning Attacks in Federated Learning: A Survey

Poisoning Attacks in Federated Learning: A Survey

Performance Weighting for Robust Federated Learning Against Corrupted Sources

On the Security & Privacy in Federated Learning

Contact Info

Product

Resources

About