REVIEW 2 cited by
Imperceptible Adversarial Attacks on Tabular Data
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Security of machine learning models is a concern as they may face adversarial attacks for unwarranted advantageous decisions. While research on the topic has mainly been focusing on the image domain, numerous industrial applications, in particular in finance, rely on standard tabular data. In this paper, we discuss the notion of adversarial examples in the tabular domain. We propose a formalization based on the imperceptibility of attacks in the tabular domain leading to an approach to generate imperceptible adversarial examples. Experiments show that we can generate imperceptible adversarial examples with a high fooling rate.
Forward citations
Cited by 2 Pith papers
-
Addressing Key Challenges of Adversarial Attacks and Defenses in the Tabular Domain: A Methodological Framework for Coherence and Consistency
Class-conditional anomaly detection and SHAP-based consistency checks provide a new way to score the quality of tabular adversarial samples, and a seven-attack comparison shows transferability-based attacks are the ha...
-
Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations
A random-shuffle attack that preserves one-dimensional feature distributions while destroying correlations can fool classifiers and, used as data augmentation, occasionally beats standard tabular generators on AUROC.
Discussion (0). Continue with ORCID to comment.