<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
This is an announcement of Wenxin Ding's MS Presentation<br class="">
===============================================<br class="">
Candidate: Wenxin Ding<br class="">
<br class="">
Date: Friday, February 23, 2024<br class="">
<br class="">
Time: 10 am CST<br class="">
<br class="">
Remote Location: <a href="https://uchicago.zoom.us/j/94076312336?pwd=YmYrQ2RjTGRnUHR4MForVzhFODVwdz09" class="">https://uchicago.zoom.us/j/94076312336?pwd=YmYrQ2RjTGRnUHR4MForVzhFODVwdz09</a><br class="">
<br class="">
Location: JCL 298<br class="">
<br class="">
Title: Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker<br class="">
<br class="">
Abstract: Finding classifiers robust to adversarial examples is critical for their safe deployment. Determining the robustness of the best possible classifier under a given threat model for a fixed data distribution and comparing it to that achieved by state-of-
the-art training methods is thus an important diagnostic tool. In this paper, we find achievable information-theoretic lower bounds on robust loss in the presence of a test-time attacker for multi-class classifiers on any discrete dataset. We provide a general
framework for finding the optimal 0 − 1 loss that revolves around the construction of a conflict hypergraph from the data and adversarial constraints. The prohibitive cost of this formulation in practice leads us to formulate other variants of the attacker-classifier
game that more efficiently determine the range of the optimal loss. Our valuation shows, for the first time, an analysis of the gap to optimal robustness for classifiers in the multi-class setting on benchmark datasets.<br class="">
<br class="">
Advisors: Heather Zheng and Ben Zhao<br class="">
<br class="">
Committee Members: Ben Zhao, Heather Zheng, and Yuxin Chen<br class="">
<div class="">
<div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
<div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
<div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
<br class="Apple-interchange-newline">
</div>
<br class="Apple-interchange-newline">
</div>
<br class="Apple-interchange-newline">
</div>
<br class="Apple-interchange-newline">
<br class="Apple-interchange-newline">
</div>
<br class="">
</body>
</html>