paper-with-me

Papers

Adversarial training for tabular data with attack propagation

2023-07-28 · Tiago Leon Melo, João Bravo, Marco O. P. Sampaio, Paolo Romano, Hugo Ferreira, João Tiago Ascensão, Pedro Bizarro

Adversarial attacks are a major concern in security-centered applications, where malicious actors continuously try to mislead Machine Learning (ML) models into wrongly classifying fraudulent activity as legitimate, whereas system maintainers try to stop them. Adversarially training ML models that are robust against such attacks can prevent business losses and reduce the work load of system maintainers. In such applications data is often tabular and the space available for attackers to manipulate undergoes complex feature engineering transformations, to provide useful signals for model training, to a space attackers cannot access. Thus, we propose a new form of adversarial training where attacks are propagated between the two spaces in the training loop. We then test this method empirically on a real world dataset in the domain of credit card fraud detection. We show that our method can prevent about 30% performance drops under moderate attacks and is essential under very aggressive attacks, with a trade-off loss in performance under no attacks smaller than 7%.

📄 PDF Abstract BibTeX arXiv:2307.15677

Code (0)

등록된 구현이 없습니다.

Tasks

Feature EngineeringFraud Detection

Similar Papers 제목 키워드 기반

Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data

2023-11-08 · Thibault Simonetto, Salah Ghamizi, Antoine Desjardins, Maxime Cordy 외

State-of-the-art deep learning models for tabular data have recently achieved acceptable performance to be deployed in industrial settings. However, the robustness of these models remains scarcely explored. Contrary to c…

Adversarial Robustness

TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Data

2025-05-27 · Zhipeng He, Chun Ouyang, Lijie Wen, Cong Liu 외

Adversarial attacks pose a significant threat to machine learning models by inducing incorrect predictions through imperceptible perturbations to input data. While these attacks have been extensively studied in unstructu…

Adversarial Attack

On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses

2025-06-03 · Mohamed Djilani, Thibault Simonetto, Karim TIT, Florian Tambon 외

Recent tabular Foundational Models (FM) such as TabPFN and TabICL, leverage in-context learning to achieve strong performance without gradient updates or fine-tuning. However, their robustness to adversarial manipulation…

In-Context Learning

Imperceptible Adversarial Attacks on Tabular Data

2019-11-08 · Vincent Ballet, Xavier Renard, Jonathan Aigrain, Thibault Laugel 외

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 …

BIG-bench Machine Learning

Investigating Imperceptibility of Adversarial Attacks on Tabular Data: An Empirical Analysis

2024-07-16 · Zhipeng He, Chun Ouyang, Laith Alzubaidi, Alistair Barros 외

Adversarial attacks are a potential threat to machine learning models by causing incorrect predictions through imperceptible perturbations to the input data. While these attacks have been extensively studied in unstructu…

Adversarial Attack