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

On the Anonymity of Peer-To-Peer Network Anonymity Schemes Used...

Piyush Kumar Sharma (imec-COSIC, KU Leuven), Devashish Gosain (Max Planck Institute for Informatics), Claudia Diaz (Nym Technologies, SA and imec-COSIC, KU Leuven)

Read More

Thwarting Smartphone SMS Attacks at the Radio Interface Layer

Haohuang Wen (Ohio State University), Phillip Porras (SRI International), Vinod Yegneswaran (SRI International), Zhiqiang Lin (Ohio State University)

Read More

WIP: Infrared Laser Reflection Attack Against Traffic Sign Recognition...

Takami Sato (University of California, Irvine), Sri Hrushikesh Varma Bhupathiraju (University of Florida), Michael Clifford (Toyota InfoTech Labs), Takeshi Sugawara (The University of Electro-Communications), Qi Alfred Chen (University of California, Irvine), Sara Rampazzi (University of Florida)

Read More

Learning Automated Defense Strategies Using Graph-Based Cyber Attack Simulations

Jakob Nyber, Pontus Johnson (KTH Royal Institute of Technology)

Read More