Klim Kireev (EPFL), Bogdan Kulynych (EPFL), Carmela Troncoso (EPFL)

Many safety-critical applications of machine learning, such as fraud or abuse detection, use data in tabular domains. Adversarial examples can be particularly damaging for these applications. Yet, existing works on adversarial robustness primarily focus on machine-learning models in image and text domains. We argue that, due to the differences between tabular data and images or text, existing threat models are not suitable for tabular domains. These models do not capture that the costs of an attack could be more significant than imperceptibility, or that the adversary could assign different values to the utility obtained from deploying different adversarial examples. We demonstrate that, due to these differences, the attack and defense methods used for images and text cannot be directly applied to tabular settings. We address these issues by proposing new cost and utility-aware threat models that are tailored to the adversarial capabilities and constraints of attackers targeting tabular domains. We introduce a framework that enables us to design attack and defense mechanisms that result in models protected against cost or utility-aware adversaries, for example, adversaries constrained by a certain financial budget. We show that our approach is effective on three datasets corresponding to applications for which adversarial examples can have economic and social implications.

View More Papers

A Systematic Study of the Consistency of Two-Factor Authentication...

Sanam Ghorbani Lyastani (CISPA Helmholtz Center for Information Security, Saarland University), Michael Backes (CISPA Helmholtz Center for Information Security), Sven...

Read More

Fine-Grained Trackability in Protocol Executions

Ksenia Budykho (Surrey Centre for Cyber Security, University of Surrey, UK), Ioana Boureanu (Surrey Centre for Cyber Security, University of...

Read More

FUZZILLI: Fuzzing for JavaScript JIT Compiler Vulnerabilities

Samuel Groß (Google), Simon Koch (TU Braunschweig), Lukas Bernhard (Ruhr-University Bochum), Thorsten Holz (CISPA Helmholtz Center for Information Security), Martin...

Read More

Trellis: Robust and Scalable Metadata-private Anonymous Broadcast

Simon Langowski (Massachusetts Institute of Technology), Sacha Servan-Schreiber (Massachusetts Institute of Technology), Srinivas Devadas (Massachusetts Institute of Technology)

Read More