Insights on Adversarial Attacks for Tabular Machine Learning via a Systematic Literature Review

2025-06-18

AI Summary

This study addresses the fragmented and unsystematic state of research on adversarial attacks against machine learning models for tabular data. We conduct the first systematic literature review (SLR) specifically targeting this domain. Through cross-study meta-analysis and formal modeling of attack strategies, we propose a multidimensional taxonomy encompassing attack paradigms, realistic constraints—categorized into data-, model-, and scenario-specific limitations—and applicability boundaries. Our analysis identifies critical challenges, including the absence of standardized robustness evaluation metrics and limited transferability of adversarial examples across models or datasets. Furthermore, we pinpoint practical deployment bottlenecks and articulate key open problems. The resulting framework establishes a unified analytical foundation for adversarial robustness research in tabular ML and provides concrete directions for future work, bridging theoretical insights with real-world applicability.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Adversarial attacks in machine learning have been extensively reviewed in areas like computer vision and NLP, but research on tabular data remains scattered. This paper provides the first systematic literature review focused on adversarial attacks targeting tabular machine learning models. We highlight key trends, categorize attack strategies and analyze how they address practical considerations for real-world applicability. Additionally, we outline current challenges and open research questions. By offering a clear and structured overview, this review aims to guide future efforts in understanding and addressing adversarial vulnerabilities in tabular machine learning.

Problem

• Review adversarial attacks on tabular machine learning models
• Categorize attack strategies for real-world applicability
• Outline challenges and open research questions

Innovation

• First systematic review on tabular adversarial attacks
• Categorizes attack strategies for tabular data
• Analyzes real-world applicability of attacks