<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T18:33:19Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/23294" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/23294</identifier><datestamp>2026-05-13T14:25:45Z</datestamp><setSpec>com_10012_9924</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9930</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author">Dunne, Murray</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2026-05-13T14:25:45Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2026-05-13T14:25:45Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2026-05-13</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2026-05-06</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/10012/23294</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">Vibe coding is the process of using a Large Language Model (LLM) to iteratively generate
software code. It is popular, with 36% of workers at technology companies reporting
adoption of generative artificial intelligence for software engineering in 2024 [1]. At this
rate of use, LLM-generated code is quickly becoming part of the embedded-systems that
comprise our everyday cyber-physical infrastructure. Most of this infrastructure is built
on C language code [2]. LLM-generated C code poses threats to dependability, exhibiting
faults such as buffer overflows, out-of-bounds writes, integer overflows, and more. In this
work, we contribute methods for improving the dependability of these systems in three key
parts: providing a real-world benchmark dataset for evaluating LLM-generated C code,
protecting LLM code generation from poisoning attacks, and detecting changes in production
embedded systems through power side-channel analysis.

This work begins with an examination and categorization of weaknesses in LLMgenerated
C code for embedded systems networking. Our findings suggest that LLMs
perform poorly at programming tasks involving direct interactions with memory. Scores
on existing LLM-generated C benchmarks do not adequately express this difficulty, as these
benchmarks do not include sufficiently real-world C programming challenges. To support
future testing of LLMs, we introduce EmbedEvalC, a dataset of C coding challenges to
provide a benchmark against which LLMs can be evaluated on real-world tasks.

Retrieval Augmented Code Generation (RACG) is an essential tool for vibe coding, but
presents new threats to dependability from poisoning attacks. If an attacker can cause a
RACG system to retrieve their crafted documents, they can induce the LLM to generate
code with weaknesses. To detect this attack, we introduce canary functions, a process by
which specific functions in the codebase are regenerated and re-tested to determine whether
the addition of new documents induces new weaknesses.

Finally, we consider the black-box setting where a systems integrator seeks to detect
unexpected changes in embedded firmware. Such changes will only become more common
with the proliferation of vibe coding. We suggest using power side-channel analysis to
provide a feedback mechanism to a fuzzer in order to determine if a fuzzing input has
caused a new response from the system. We show that responses involving five or more
memory-interacting instructions are consistently detectable.

In this work, we suggest a collection of techniques to mitigate risks to the dependability
of embedded systems posed by LLM-generated C code.

Abstract Citations:
[1] Alex Singla, Alexander Sukharevsky, Lareina Yee, Michael Chui, and Bryce Hall. &amp;quot;The state of AI: How organizations are rewiring to capture value&amp;quot;, McKinsey &amp;amp; Company, March 2025.
[2] P. Soulier, D. Li, and J. R. Williams, “A Survey of Language-Based Approaches to Cyber-Physical and Embedded System Development,” Tsinghua Science and Technology, vol. 20, no. 2, pp. 130–141, 2015.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="relation" qualifier="uri">https://github.com/murraydunne/EmbedEvalC</dim:field>
   <dim:field mdschema="dc" element="subject">large language models</dim:field>
   <dim:field mdschema="dc" element="subject">code generation</dim:field>
   <dim:field mdschema="dc" element="subject">security</dim:field>
   <dim:field mdschema="dc" element="subject">embedded systems</dim:field>
   <dim:field mdschema="dc" element="title">Mitigating Risks to Dependability from Vibe-Coding C for Embedded Systems</dim:field>
   <dim:field mdschema="dc" element="type">Doctoral Thesis</dim:field>
   <dim:field mdschema="dc" element="pending">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department">David R. Cheriton School of Computer Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline">Computer Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="grantor" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="uws-etd" element="degree">Doctor of Philosophy</dim:field>
   <dim:field mdschema="uws-etd" element="embargo" qualifier="terms">0</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Fischmeister, Sebastian</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="affiliation1">Faculty of Mathematics</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="city" lang="en">Waterloo</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="country" lang="en">Canada</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="province" lang="en">Ontario</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>