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

2025/06/18 by Salijona Dyrmishi, Mohamed Djilani, Dyrmishi, Salijona +7
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2506.15506

openalex publication_date 2025/06/18 · openalex created_date 2025/10/19 · openalex updated_date 2026/07/28

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.

Citations

• RobustBlack: Challenging Black-Box Adversarial Attacks on State-of-the-Art Defenses
• TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling
• Deep generative models as an adversarial attack strategy for tabular machine learning
• TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
• Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
• CaFA: Cost-aware, Feasible Attacks With Database Constraints Against Neural Tabular Classifiers
• MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception
• How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data
• Towards Efficient and Domain-Agnostic Evasion Attack with High-dimensional Categorical Inputs
• Adversarial Robustness for Tabular Data through Cost and Utility Awareness
• On The Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attacks
• A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space
• Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS
• Feature Importance Guided Attack: A Model Agnostic Adversarial Attack
• On the Robustness of Domain Constraints
• Adversarial Robustness with Non-uniform Perturbations
• Adversarial Examples in Constrained Domains
• The PRISMA 2020 statement: an updated guideline for reporting systematic reviews
• Adversarial Machine Learning in Network Intrusion Detection Systems
• ConAML: Constrained Adversarial Machine Learning for Cyber-Physical Systems
• Imperceptible Adversarial Attacks on Tabular Data
• FENCE: Feasible Evasion Attacks on Neural Networks in Constrained Environments
• Stateful Detection of Black-Box Adversarial Attacks
• DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications
• Theoretically Principled Trade-off between Robustness and Accuracy
• Feature Denoising for Improving Adversarial Robustness
• EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
• Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
• DeltaPhish: Detecting Phishing Webpages in Compromised Websites
• Towards Deep Learning Models Resistant to Adversarial Attacks
• DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples
• Towards Evaluating the Robustness of Neural Networks
• Adversarial examples in the physical world
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• The Limitations of Deep Learning in Adversarial Settings
• DeepFool: a simple and accurate method to fool deep neural networks
• Intriguing properties of neural networks

Related

• TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Data
• Imperceptible Adversarial Attacks on Tabular Data
• TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
• Addressing Key Challenges of Adversarial Attacks and Defenses in the Tabular Domain: A Methodological Framework for Coherence and Consistency
• Fast Adversarial Label-Flipping Attack on Tabular Data