Work

Amplified Gradient Inversion Attacks on Federated Learning Frameworks

Year: 2024

Type: article

Abstract: Federated Learning (FL) facilitates collaborative model training while safeguarding data privacy, making it ideal for sensitive fields such as finance, education, and healthcare. Despite its promise, FL remains vulnerable to privacy breaches, particularly through gradient inversion attacks that can reconstruct private data from shared model updates. This research introduces a nonlinear amplification strategy that enhances the potency of such attacks, revealing heightened risks of data leakage in FL environments. Additionally, we evaluate the resilience of privacy-preserving mechanisms, such as Differential Privacy (DP) and Homomorphic Encryption (HE), by employing two proposed metrics AvgSSIM and AvgMSE to measure both the severity of attacks and the efficacy of defenses.

Source: Journal of Science and Technology on Information security

DOI: 10.54654/isj.v3i23.1066

Authors: Tran Anh Tu, Dinh Cong Thanh, Tran Duc Su

Institutions: Academy of Cryptography Techniques, Posts and Telecommunications Institute of Technology

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

OpenAlex ID: W4405586851

FWCI:

Cites: 17

Cited by:

Related to: 10