Survey of Security and Data Attacks on Machine Unlearning In Financial and E-Commerce

TL;DR

This survey reviews security and data attacks on machine unlearning in finance and e-commerce, discussing threats, attack methods, and defense strategies to protect data privacy and model integrity.

Contribution

It provides a comprehensive overview of attack types and defense mechanisms for secure machine unlearning in critical financial and e-commerce applications.

Findings

Membership inference and data reconstruction attacks threaten data privacy.

Data poisoning and unlearning request attacks compromise model integrity.

Defense strategies include differential privacy and cryptographic techniques.

Abstract

This paper surveys the landscape of security and data attacks on machine unlearning, with a focus on financial and e-commerce applications. We discuss key privacy threats such as Membership Inference Attacks and Data Reconstruction Attacks, where adversaries attempt to infer or reconstruct data that should have been removed. In addition, we explore security attacks including Machine Unlearning Data Poisoning, Unlearning Request Attacks, and Machine Unlearning Jailbreak Attacks, which target the underlying mechanisms of unlearning to manipulate or corrupt the model. To mitigate these risks, various defense strategies are examined, including differential privacy, robust cryptographic guarantees, and Zero-Knowledge Proofs (ZKPs), offering verifiable and tamper-proof unlearning mechanisms. These approaches are essential for safeguarding data integrity and privacy in high-stakes financial and e-commerce contexts, where compromised models can lead to fraud, data leaks, and reputational damage. This survey highlights the need for continued research and innovation in secure machine unlearning, as well as the importance of developing strong defenses against evolving attack vectors.