CrashTranslator: Automatically Reproducing Mobile Application Crashes
Directly from Stack Trace
- URL: http://arxiv.org/abs/2310.07128v1
- Date: Wed, 11 Oct 2023 02:00:18 GMT
- Title: CrashTranslator: Automatically Reproducing Mobile Application Crashes
Directly from Stack Trace
- Authors: Yuchao Huang, Junjie Wang, Zhe Liu, Yawen Wang, Song Wang, Chunyang
Chen, Yuanzhe Hu, Qing Wang
- Abstract summary: This paper proposes an approach named CrashTranslator to automatically reproduce mobile application crashes directly from the stack trace.
We evaluate CrashTranslator on 75 crash reports involving 58 popular Android apps, and it successfully reproduces 61.3% of the crashes.
- Score: 30.48737611250448
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Crash reports are vital for software maintenance since they allow the
developers to be informed of the problems encountered in the mobile
application. Before fixing, developers need to reproduce the crash, which is an
extremely time-consuming and tedious task. Existing studies conducted the
automatic crash reproduction with the natural language described reproducing
steps. Yet we find a non-neglectable portion of crash reports only contain the
stack trace when the crash occurs. Such stack-trace-only crashes merely reveal
the last GUI page when the crash occurs, and lack step-by-step guidance.
Developers tend to spend more effort in understanding the problem and
reproducing the crash, and existing techniques cannot work on this, thus
calling for a greater need for automatic support. This paper proposes an
approach named CrashTranslator to automatically reproduce mobile application
crashes directly from the stack trace. It accomplishes this by leveraging a
pre-trained Large Language Model to predict the exploration steps for
triggering the crash, and designing a reinforcement learning based technique to
mitigate the inaccurate prediction and guide the search holistically. We
evaluate CrashTranslator on 75 crash reports involving 58 popular Android apps,
and it successfully reproduces 61.3% of the crashes, outperforming the
state-of-the-art baselines by 109% to 206%. Besides, the average reproducing
time is 68.7 seconds, outperforming the baselines by 302% to 1611%. We also
evaluate the usefulness of CrashTranslator with promising results.
Related papers
- Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps [23.460238111094608]
ReBL is a novel feedback-driven approach to reproduce Android bug reports.
It employs innovative prompts to enhance GPT's contextual reasoning.
It successfully reproduced 90.63% of crash and 23 non-crash bug reports.
arXiv Detail & Related papers (2024-07-06T19:58:03Z) - VDebugger: Harnessing Execution Feedback for Debugging Visual Programs [103.61860743476933]
We introduce V Debugger, a critic-refiner framework trained to localize and debug visual programs by tracking execution step by step.
V Debugger identifies and corrects program errors leveraging detailed execution feedback, improving interpretability and accuracy.
Evaluations on six datasets demonstrate V Debugger's effectiveness, showing performance improvements of up to 3.2% in downstream task accuracy.
arXiv Detail & Related papers (2024-06-19T11:09:16Z) - Learning Traffic Crashes as Language: Datasets, Benchmarks, and What-if Causal Analyses [76.59021017301127]
We propose a large-scale traffic crash language dataset, named CrashEvent, summarizing 19,340 real-world crash reports.
We further formulate the crash event feature learning as a novel text reasoning problem and further fine-tune various large language models (LLMs) to predict detailed accident outcomes.
Our experiments results show that our LLM-based approach not only predicts the severity of accidents but also classifies different types of accidents and predicts injury outcomes.
arXiv Detail & Related papers (2024-06-16T03:10:16Z) - Crash Report Accumulation During Continuous Fuzzing [0.0]
We propose a crash accumulation method and implement it as part of the CASR toolset.
We evaluate our approach on crash reports collected from fuzzing results.
arXiv Detail & Related papers (2024-05-28T13:36:31Z) - The Impact Of Bug Localization Based on Crash Report Mining: A Developers' Perspective [7.952391285456257]
We report our experience of using an approach for grouping crash reports and finding buggy code on a weekly basis for 18 months.
The approach investigated in this study correctly suggested the buggy file most of the time -- the approach's precision was around 80%.
arXiv Detail & Related papers (2024-03-16T01:23:01Z) - CrashFormer: A Multimodal Architecture to Predict the Risk of Crash [1.3194391758295112]
Accident prediction is key to improving traffic safety, enabling proactive measures to be taken before a crash occurs.
We propose CrashFormer, a multi-modal architecture that utilizes comprehensive inputs such as the history of accidents, weather information, map images, and demographic information.
The model predicts the future risk of accidents on a reasonably acceptable cadence (i.e. every six hours) for a geographical location of 5.161 square kilometers.
arXiv Detail & Related papers (2024-02-07T13:09:23Z) - Teaching Large Language Models to Self-Debug [62.424077000154945]
Large language models (LLMs) have achieved impressive performance on code generation.
We propose Self- Debugging, which teaches a large language model to debug its predicted program via few-shot demonstrations.
arXiv Detail & Related papers (2023-04-11T10:43:43Z) - DeepAccident: A Motion and Accident Prediction Benchmark for V2X
Autonomous Driving [76.29141888408265]
We propose a large-scale dataset containing diverse accident scenarios that frequently occur in real-world driving.
The proposed DeepAccident dataset includes 57K annotated frames and 285K annotated samples, approximately 7 times more than the large-scale nuScenes dataset.
arXiv Detail & Related papers (2023-04-03T17:37:00Z) - Large-scale Crash Localization using Multi-Task Learning [3.4383679424643456]
We develop a novel multi-task sequence labeling approach for identifying blamed frames in stack traces.
We evaluate our model with over a million real-world crashes from four popular Microsoft applications.
arXiv Detail & Related papers (2021-09-29T10:26:57Z) - Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object
Detection [55.12894776039135]
State-of-the-art 3D object detectors, based on deep learning, have shown promising accuracy but are prone to over-fit to domain idiosyncrasies.
We propose a novel learning approach that drastically reduces this gap by fine-tuning the detector on pseudo-labels in the target domain.
We show, on five autonomous driving datasets, that fine-tuning the detector on these pseudo-labels substantially reduces the domain gap to new driving environments.
arXiv Detail & Related papers (2021-03-26T01:18:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.