<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Program Analysis | Hulin Wang</title><link>https://www.hulinwang.me/tag/program-analysis/</link><atom:link href="https://www.hulinwang.me/tag/program-analysis/index.xml" rel="self" type="application/rss+xml"/><description>Program Analysis</description><generator>Wowchemy (https://wowchemy.com)</generator><language>en-us</language><lastBuildDate>Wed, 01 Apr 2026 00:00:00 +0000</lastBuildDate><image><url>https://www.hulinwang.me/media/sharing.png</url><title>Program Analysis</title><link>https://www.hulinwang.me/tag/program-analysis/</link></image><item><title>Root-Cause-Driven Vulnerability Repair</title><link>https://www.hulinwang.me/project/root-cause-repair/</link><pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate><guid>https://www.hulinwang.me/project/root-cause-repair/</guid><description>&lt;p>&lt;strong>Status:&lt;/strong> First-author paper, under submission. Ph.D. research at ASU SEFCOM.&lt;/p>
&lt;ul>
&lt;li>Designed a two-stage repair pipeline combining static and dynamic analysis to locate potential root causes, capturing defects that span multiple code locations and indirect calls missed by static-only tools such as CodeQL.&lt;/li>
&lt;li>Supplied root-cause candidates to a lightweight patching agent with repository-search and file-editing tools, so repairs are informed by the relevant code context.&lt;/li>
&lt;li>Built a manually annotated patch-quality dataset covering &lt;strong>178 C/C++ vulnerabilities&lt;/strong> to compare repairs generated by multiple agents.&lt;/li>
&lt;li>Improved patch quality by &lt;strong>20%&lt;/strong> over baseline methods, validated by majority vote of three human experts.&lt;/li>
&lt;/ul>
&lt;h3 id="related-llm-assisted-fuzzing-for-occluded-bugs">Related: LLM-assisted fuzzing for occluded bugs&lt;/h3>
&lt;p>An LLM-assisted patching + AFL++ pipeline that surfaces vulnerabilities masked by more easily triggered crashes. Automated crash clustering, root-cause hints, LLM-guided edits, and re-fuzzing reduced false positives from 90% to 30% and found &lt;strong>20+ distinct occluded vulnerabilities per target&lt;/strong> in Objdump, FFmpeg, and GPAC.&lt;/p></description></item></channel></rss>