What type of study is this?

This is a Experimental Study study.

October 10, 2025Open Access

Boundary on the Table: Efficient Black-Box Decision-Based Attacks for Structured Data

View Full Paper

Ask AI

Bookmark

Authors

Novel attack method reveals critical vulnerabilities in tabular data models, suggesting urgent defense enhancements.

The introduced attack achieves over 90% success rates across various models, highlighting the risk in tabular data.
By minimizing oracle access, the gradient-free method efficiently navigates both discrete and continuous feature spaces.
Extensive experiments validate the attack's effectiveness against traditional classifiers and LLM-based systems.
The results demonstrate a significant vulnerability in structured data models, indicating a pressing need for improved defenses.

Kazoom et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

October 10, 2025Open Access

View Full Paper

Ask AI

Bookmark

Authors

Novel attack method reveals critical vulnerabilities in tabular data models, suggesting urgent defense enhancements.

The introduced attack achieves over 90% success rates across various models, highlighting the risk in tabular data.
By minimizing oracle access, the gradient-free method efficiently navigates both discrete and continuous feature spaces.
Extensive experiments validate the attack's effectiveness against traditional classifiers and LLM-based systems.
The results demonstrate a significant vulnerability in structured data models, indicating a pressing need for improved defenses.

Kazoom et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark