GPTrace: Effective Crash Deduplication Using LLM Embeddings
By: Patrick Herter , Vincent Ahlrichs , Ridvan Açilan and more
Potential Business Impact:
Finds duplicate software bugs faster.
Fuzzing is a highly effective method for uncovering software vulnerabilities, but analyzing the resulting data typically requires substantial manual effort. This is amplified by the fact that fuzzing campaigns often find a large number of crashing inputs, many of which share the same underlying bug. Crash deduplication is the task of finding such duplicate crashing inputs and thereby reducing the data that needs to be examined. Many existing deduplication approaches rely on comparing stack traces or other information that is collected when a program crashes. Although various metrics for measuring the similarity of such pieces of information have been proposed, many do not yield satisfactory deduplication results. In this work, we present GPTrace, a deduplication workflow that leverages a large language model to evaluate the similarity of various data sources associated with crashes by computing embedding vectors and supplying those as input to a clustering algorithm. We evaluate our approach on over 300 000 crashing inputs belonging to 50 ground truth labels from 14 different targets. The deduplication results produced by GPTrace show a noticeable improvement over hand-crafted stack trace comparison methods and even more complex state-of-the-art approaches that are less flexible.
Similar Papers
LibLMFuzz: LLM-Augmented Fuzz Target Generation for Black-box Libraries
Cryptography and Security
Finds hidden problems in computer programs automatically.
MirrorFuzz: Leveraging LLM and Shared Bugs for Deep Learning Framework APIs Fuzzing
Software Engineering
Finds hidden bugs in AI tools.
FalseCrashReducer: Mitigating False Positive Crashes in OSS-Fuzz-Gen Using Agentic AI
Software Engineering
AI finds bugs without making mistakes.