CaFA: Cost-aware, Feasible Attacks With Database Constraints Against Neural Tabular Classifiers
Authors:
- Nave FrostNFNave Frost
- 19 May 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1345-1364
Abstract
This work presents CaFA, a system for Cost-aware Feasible Attacks for assessing the robustness of neural tabular classifiers against adversarial examples realizable in the problem space, while minimizing adversaries’ effort. To this end, CaFA leverages TabPGD—an algorithm we set forth to generate adversarial perturbations suitable for tabular data— and incorporates integrity constraints automatically mined by state-of-the-art database methods. After producing adversarial examples in the feature space via TabPGD, CaFA projects them on the mined constraints, leading, in turn, to better attack realizability. We tested CaFA with three datasets and two architectures and found, among others, that the constraints we use are of higher quality (measured via soundness and completeness) than ones employed in prior work. Moreover, CaFA achieves higher feasible success rates—i.e., it generates adversarial examples that are often misclassified while satisfying constraints—than prior attacks while simultaneously perturbing few features with lower magnitudes, thus saving effort and improving inconspicuousness. We open-source CaFA, 1 hoping it will serve as a generic system enabling machine-learning engineers to assess their models’ robustness against realizable attacks, thus advancing deployed models’ trustworthiness.Keywords
All Related Versions
Funding Information
- European Research Council
This publication has 35 references indexed in Scilit:
- Accessorize in the Dark: A Security Analysis of Near-Infrared Face Recognition2024
- Not all datasets are born equal: On heterogeneous tabular data and adversarial examplesKnowledge-Based Systems, 2022
- A new hybrid ensemble feature selection framework for machine learning-based phishing detection systemInformation Sciences, 2019
- Constraints-Based Explanations of Classifications2019
- Wild patterns: Ten years after the rise of adversarial machine learningPattern Recognition, 2018
- Adversarial Examples for Malware Detection2017
- The Limitations of Deep Learning in Adversarial Settings2016
- A data-driven approach to predict the success of bank telemarketingDecision Support Systems, 2014
- Evasion Attacks against Machine Learning at Test Time2013
- Z3: An Efficient SMT Solver2008