<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="">
<i class="">Department of Computer Science Seminar</i>
<div class=""><i class=""><br class="">
</i></div>
<div class=""><b style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">Bo Li</b></div>
<div class=""><b style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">Assistant Professor, Department of Computer Science</b></div>
<div class=""><b style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">University of Illinois Urbana-Champaign</b></div>
<div class=""><span style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class=""><b class=""><br class="">
</b></span></div>
<div class=""><b style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">Wednesday, January 18th</b></div>
<div class=""><b style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">3:00pm - 4:00pm</b></div>
<div class=""><b style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">In Person: John Crerar Library 390</b></div>
<div class=""><span style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class=""><b class=""><br class="">
</b></span></div>
<div class=""><b class="">Zoom</b></div>
<div class=""><b class=""><a href="https://uchicagogroup.zoom.us/j/91636415129?pwd=T1RRYUNXTWtyN0JUWUZFWmcwY3lydz09" class="">https://uchicagogroup.zoom.us/j/91636415129?pwd=T1RRYUNXTWtyN0JUWUZFWmcwY3lydz09</a></b></div>
<div class=""><br class="">
</div>
<div class=""><span style="font-weight: 700;" class="">Meeting ID: 916 3641 5129</span></div>
<div class=""><span style="font-weight: 700;" class="">Passcode: 675319</span></div>
<div class=""><b class=""><br class="">
</b></div>
<div class=""><b style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">Title: </b><span style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class=""><b class="">Certifiably
Robust Learning via Knowledge-Enabled Logical Reasoning</b></span></div>
<div class=""><span style="text-align: justify; font-weight: bold; caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class=""><br class="">
</span></div>
<div class=""><span style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class=""><b class="">Abstract:</b></span></div>
<div class=""><span style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class=""><br class="">
</span></div>
<div class=""><span style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">As intelligent systems become pervasive, safeguarding their trustworthiness is critical. Standard machine learning (ML) approaches
often assume that the training and test data follow similar distributions, without taking into account the possibility of adversaries manipulating either distribution or natural distribution shifts. This can lead to severe trustworthiness issues in ML. For
instance, our past work has shown that motivated adversaries can circumvent anomaly detection or other machine learning models at test-time through evasion attacks, or inject well-crafted malicious instances into training data to induce errors through poisoning
attacks. In this talk, I will provide a brief overview of my research on trustworthy machine learning, including robustness, privacy, generalization, and their underlying interconnections, with a focus on robustness. In particular, I will first discuss the
current state of the art in certifiably robust defenses based on purely data-driven learning approaches and their limitations. I will then present our </span><i style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">certifiably
robust learning via knowledge-enabled logical reasoning</i><span style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class=""> approach, including a thorough analysis of its properties. I will demonstrate that
it is possible to 1) certify the robustness of this end-to-end approach, which significantly improves the SOTA certified robustness, 2) prove this approach is more robust than a single ML model under mild conditions, 3) make it scalable for a variety of downstream
tasks, and this approach is agnostic to the tasks, data, and attacks being used. </span></div>
<div class=""><span style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class=""><br class="">
</span></div>
<div class=""><span style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class=""><b class="">Bio:</b></span></div>
<div class="">
<p style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">
<a href="http://boli.cs.illinois.edu" class="">Dr. Bo Li</a> is an assistant professor in the Department of Computer Science at the University of Illinois at Urbana–Champaign. She is the recipient of the IJCAI Computers and Thought Award, Alfred P. Sloan Research
Fellowship, AI’s 10 to Watch, NSF CAREER Award, MIT Technology Review TR-35 Award, Dean's Award for Excellence in Research, C.W. Gear Outstanding Junior Faculty Award, Intel Rising Star award, Symantec Research Labs Fellowship, Rising Star Award, Research
Awards from Tech companies such as Amazon, Facebook, Intel, IBM, and eBay, and best paper awards at several top machine learning and security conferences. Her research focuses on both theoretical and practical aspects of trustworthy machine learning, which
is at the intersection of machine learning, security, privacy, and game theory. She has designed several scalable frameworks for trustworthy machine learning and privacy-preserving data publishing systems.Her work has been featured by major publications and
media outlets such as Nature, Wired, Fortune, and New York Times.</p>
<div class=""><br class="">
</div>
</div>
<div class=""><img apple-inline="yes" id="F159EE62-D8FD-44F3-8A88-B07F6564EF5B" class="" width="320" height="214" src="cid:F20A9C31-2828-4C3F-A185-F6CA05AF7ED2"><span style="font-family: "Times New Roman", serif; text-align: justify; font-weight: bold; caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">
</span><span style="font-family: "Times New Roman", serif; text-align: justify; font-weight: bold; caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class=""> </span></div>
<div class=""><span style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class=""><b class=""></b></span></div>
<div class=""><b class=""><font color="#3c4043" class=""><span style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;" class="">----<br class="">
</span></font></b>
<div class="">
<div>Holly Santos<br class="">
Executive Assistant to Michael J. Franklin, Chairman<br class="">
Department of Computer Science<br class="">
The University of Chicago<br class="">
5730 S Ellis Ave-217 Chicago, IL 60637<br class="">
P: 773-834-8977<br class="">
<a href="mailto:hsantos@uchicago.edu" class="">hsantos@uchicago.edu</a></div>
<div class=""><br class="">
</div>
<br class="Apple-interchange-newline">
</div>
<br class="">
</div>
</body>
</html>