Understanding Deep Gradient Leakage via Inversion Influence Functions

2023/09/22 by Haobo Zhang, Zhang, Haobo, Junyuan Hong +7 · 1 citation
Computer Science · Medicine · #Adversarial Robustness in Machine Learning #COVID-19 diagnosis using AI #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data

paper · doi:10.48550/arxiv.2309.13016

openalex publication_date 2023/09/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

F effectively approximated the DGL generally on different model architectures, datasets, modalities, attack implementations, and perturbation-based defenses. With this novel tool, we provide insights into effective gradient perturbation directions, the unfairness of privacy protection, and privacy-preferred model initialization. Our codes are provided in https://github.com/illidanlab/inversion-influence-function.

Cited by

• Uncovering Privacy Vulnerabilities through Analytical Gradient Inversion Attacks

Related

• Uncovering Privacy Vulnerabilities through Analytical Gradient Inversion Attacks
• Deep Leakage from Gradients
• Analysing Training-Data Leakage from Gradients through Linear Systems and Gradient Matching
• Gradient Leakage Attack Resilient Deep Learning
• Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models