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

Are some prices more equal than others? Evaluating store-based...

Hugo Jonker (Open University Netherlands), Stefan Karsch (TH Koln), Benjamin Krumnow (TH Koln), Godfried Meesters (Open University Netherlands)

Read More

OBI: a multi-path oblivious RAM for forward-and-backward-secure searchable encryption

Zhiqiang Wu (Changsha University of Science and Technology), Rui Li (Dongguan University of Technology)

Read More

Non-Interactive Privacy-Preserving Sybil-Free Authentication Scheme in VANETs

Mahdi Akil (Karlstad University), Leonardo Martucci (Karlstad University), Jaap-Henk Hoepman (Radboud University)

Read More

“I didn't click”: What users say when reporting phishing

Nikolas Pilavakis, Adam Jenkins, Nadin Kokciyan, Kami Vaniea (University of Edinburgh)

Read More