Deep Learning Model Inversion Attacks and Defenses: A Comprehensive Survey

TL;DR

This comprehensive survey addresses the privacy risks posed by deep learning model inversion (MI) attacks and surveys a wide spectrum of defenses. It provides a unified taxonomy (gradient inversion, generative-model-based, and optimization-based attacks) across diverse data types and application domains, including emergent foundation-model contexts, and highlights the trade-offs with model utility. The authors also offer a systematic literature-selection methodology, a public research repository, and a forward-looking discussion of challenges such as realistic threat models, benchmarking, and domain-specific defenses. The work aims to guide researchers and practitioners toward robust, scalable privacy protections for AI systems while preserving performance in real-world deployments.

Abstract

The rapid adoption of deep learning in sensitive domains has brought tremendous benefits. However, this widespread adoption has also given rise to serious vulnerabilities, particularly model inversion (MI) attacks, posing a significant threat to the privacy and integrity of personal data. The increasing prevalence of these attacks in applications such as biometrics, healthcare, and finance has created an urgent need to understand their mechanisms, impacts, and defense methods. This survey aims to fill the gap in the literature by providing a structured and in-depth review of MI attacks and defense strategies. Our contributions include a systematic taxonomy of MI attacks, extensive research on attack techniques and defense mechanisms, and a discussion about the challenges and future research directions in this evolving field. By exploring the technical and ethical implications of MI attacks, this survey aims to offer insights into the impact of AI-powered systems on privacy, security, and trust. In conjunction with this survey, we have developed a comprehensive repository to support research on MI attacks and defenses. The repository includes state-of-the-art research papers, datasets, evaluation metrics, and other resources to meet the needs of both novice and experienced researchers interested in MI attacks and defenses, as well as the broader field of AI security and privacy. The repository will be continuously maintained to ensure its relevance and utility. It is accessible at https://github.com/overgter/Deep-Learning-Model-Inversion-Attacks-and-Defenses.

Figures (5)

• Figure 1: A visualization example of the model inversion (MI) attack.
• Figure 2: The structured taxonomy of the MI attacks in this survey.
• Figure 3: Illustration of the differences between centralized learning (left) and federated learning (right).
• Figure 4: A demonstrative example of gradient inversion attacks vs. generative model-based attacks.
• Figure 5: MI attacks across various applications where different data types are processed.