On the Security & Privacy in Federated Learning

Authors: Gorka Abad, Stjepan Picek, Víctor Julio Ramírez-Durán, Aitor Urbieta
Published: 2021-12-10 | Updated: 2022-03-16

Source: https://arxiv.org/abs/2112.05423

PDF: https://arxiv.org/pdf/2112.05423

AIにより推定されたラベル

防御手法 ポイズニング バックドア攻撃

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Recent privacy awareness initiatives such as the EU General Data Protection Regulation subdued Machine Learning (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 that threaten FL’s confidentiality, integrity, or availability (CIA). This work assesses the CIA of FL by reviewing the state-of-the-art (SoTA) and 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 and provide promising future research directions.