<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</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=""><span class=""><b class="">Kexin Pei</b></span></div>
<div class=""><b class="">PhD Candidate, Computer Science</b></div>
<div class=""><b class="">Columbia University </b></div>
<div class=""><b class=""><br class="">
</b></div>
<div class=""><b class="">Thursday, February 2nd</b></div>
<div class=""><b class="">2:00pm - 3:00pm </b></div>
<div class=""><b class="">In Person: John Crerar Library 390</b></div>
<div class=""><b class=""><br class="">
</b></div>
<div class=""><b class="">Zoom:</b></div>
<div class=""><b class="">
<div class=""><a href="https://uchicagogroup.zoom.us/j/94203156841?pwd=WEFrL3FUZkRKZnAyOEMwWWVtZzRsZz09" class="">https://uchicagogroup.zoom.us/j/94203156841?pwd=WEFrL3FUZkRKZnAyOEMwWWVtZzRsZz09</a></div>
<div class=""><br class="">
</div>
<div class="">Meeting ID: 942 0315 6841</div>
<div class="">Passcode: 586612</div>
</b></div>
<div class=""><b class=""><br class="">
</b></div>
<div class=""><b class="">Title: Robust and Generalizable Learning for Analyzing and Securing Software</b></div>
<div class=""><b class=""><br class="">
</b></div>
<div class=""><b class="">Abstract:</b></div>
<div class="">Software is powering every aspect of our society, but it remains plagued with errors and prone to critical failures and security breaches. Program analysis has been a predominant technique for building trustworthy software. However, traditional
approaches rely on hand-curated rules tailored for specific analysis tasks and thus require significant manual effort to tune for different applications. While recent machine learning-based approaches have shown some early promise, they, too, tend to learn
spurious features and overfit to specific tasks without understand the underlying program semantics.</div>
<div class=""><br class="">
</div>
<div class="">In this talk, I will describe my research on building machine learning (ML) models toward learning program semantics so they can remain robust against transformations in program syntax and generalize to various program analysis tasks and security
applications. The corresponding research tools, such as XDA, Trex, StateFormer, and NeuDep, have outperformed commercial tools and prior arts by up to 117x in speed and by 35% in precision and have helped identify security vulnerabilities in the real-world
firmware that run on billions of devices. To ensure the developed ML models are robust and generalizable, I will briefly describe my research on building testing and verification frameworks for checking the safety properties of deep learning systems. The
corresponding research tools, such as DeepXplore, DeepTest, ReluVal, and Neurify, have been adopted and followed up by the industry (e.g. in TensorFuzz built by Google), been covered in media such as Scientific American, IEEE Spectrum, Newsweek, and TechRadar,
and inspired over thousands of follow-up projects.</div>
<div class=""><b class=""><br class="">
</b></div>
<div class=""><b class="">Bio:</b></div>
<div class="">Kexin Pei is a PhD candidate in Computer Science at Columbia University, advised by Suman Jana and Jenfeng Yang. His research lies at the intersections of security, software engineering, and machine learning with a focus on building machine-learning
tools that utilize program structure and behavior to analyze and secure software. His research has received the Best Paper Award in SOSP, a Distinguished Artifact Award, been featured in CACM Research Highlight, and won CSAW Applied Research Competition Runner-Up.
He was part of the learning for code team when he interned at Google Brain, building program analysis tools based on large language models. </div>
<div class=""><br class="">
</div>
<div class=""><img id="<f_lcs28pnn1>" alt="headshot_latest.jpg" class="Apple-web-attachment Apple-edge-to-edge-visual-media" apple-inline="yes" style="opacity: 1;" src="cid:f_lcs28pnn1"></div>
<div class="">
<div><br class="">
</div>
<div>---</div>
<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><br class="">
</div>
</div>
<br class="">
</body>
</html>