arXiv subjects

Matthew B. Dwyer

Publications and source records attributed to Matthew B. Dwyer.

At least 19 recordsLinked to original sources

arXiv2026

Latent Anchor-Driven Test Generation for Deep Neural Networks

Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essential to identify and mitigate model weaknesses. Existing DNN testing approaches explore either the input space or a learned latent space. While latent-space generation can better maintain plausibility than direct input-space mutation, current methods still face a trade-off among exploration controllability, failure diversity, and seed-relative semantic drift. To overcome these limitations, we propose Latte, a black-box testing framework that generates semantically proximate, diverse, and fault-revealing test cases by leveraging the latent space. Specifically, Latte encodes each input seed with a pre-trained VQ-VAE and performs a seed-centered, one-step latent mutation along directions defined by anchors sampled from alternative classes, followed by quantization and decoding back to the input space. This explores local neighborhoods around each seed within the learned latent manifold, resulting in a larger number and broader diversity of oracle-triggering prediction discrepancies under the same budget. We evaluated Latte on 5 datasets and 10 DNN models in single-model and multi-model testing scenarios. Across the evaluated datasets and models, Latte improves fault exposure and behavioral diversity under matched testing budgets. Under the single-model setting, it also maintains low seed-relative semantic drift with respect to the source seeds.

cs.LG↗

arXiv2026

DIFUZZI: A Differential Fuzzing Tool for Code Functional Similarity Assessment

A range of software engineering tasks, such as optimization and refactoring, seek to preserve the behavior of software components and require methods to assess functional similarity. Research has explored formal approaches to prove functional equivalence and used machine learning methods to approximate it, but the former does not scale and does not quantify the extent of similarity and the latter struggles when subtle semantic differences are present. Differential fuzzing offers a scalable approach for differencing programs semantically, but applying it often requires substantial manual effort to construct input generators that are well-suited to a target pair of programs. To address this challenge, we introduce DIFUZZI, which incorporates an LLM-based generator synthesis step that is iteratively validated and repaired. By automating this step, DIFUZZI paves the way for broader applicability of differential fuzzing. We release DIFUZZI at https://github.com/Dristi123/difuzzi_tool, with a demonstration video at https://youtu.be/FlHNOHuo9WE

cs.SE↗

arXiv2026

NeuroSTAR: Automata-guided Neuro-symbolic Specification Formalization

Automated translation of natural language (NL) descriptions into Linear Temporal Logic over finite traces (LTLf) is a prerequisite for automated formal verification of a system's dynamic behavior. Several LLM-based methods have recently shown potential for this task. However, they struggle with the nuance of natural language descriptions, which can lead LLMs to only partially capture the intended meaning. To address this limitation, we propose NeuroSTAR (Automata-guided Neuro-symbolic Specification Formalization), an NL-to-LTLf framework that builds on two insights. First, it leverages multiple generators to obtain diverse LTLf candidates. Second, it uses an automata-theoretic semantic comparison based on DFA traces to identify behavioral disagreements that guide formula refinement. We evaluate NeuroSTAR and show that it improves NL-to-LTLf translation performance by 8-18 percentage points relative to the prior state-of-the-art (SoTA) on unambiguous benchmarks. We further study its applicability to a body of driving law text, a complex, realistic, and reference-free domain critical for autonomous-vehicle specification. This study shows that NeuroSTAR can capture the necessary temporal semantics in 83.9% of the driving law sections, which demonstrates the effectiveness of automata-guided reference-free refinement in formalization.

cs.FL↗

arXiv2026

What Survives the Next Model? Benchmarking LLM-Based Techniques Against Single-Prompts

The software engineering research community has enthusiastically embraced the integration of Large Language Models (LLMs) into complex techniques to solve a wide variety of tasks. However, the extent to which this investment is strategic remains unclear, as the native capabilities of successive frontier model generations can rapidly render existing techniques obsolete. To assess this research investment, we analyze 35 LLM-based technique papers from ICSE 2026. We evaluate whether their complex tools can be outperformed by the simplest possible alternative: a single, automatically generated prompt executed on a newer generation model, without any iterative refinement. We find that for between 37% and 63% papers, a newer model with a single prompt natively outperforms the heavily engineered tooling proposed just a year prior. We identify that constructive techniques like code generation or repair are more amenable to substitution by a single-prompt. We also identify a surviving set of papers relying on strategies that provide additional insights to the model where newer LLMs will amplify the proposed technique. Our findings raise questions about the cost-benefit proposition of techniques designed as workarounds to temporary model deficits and the need to focus on enduring challenges that scale synergistically with future model generations. Our source codes and results are made publicly available at https://github.com/less-lab-uva/What-Survives-the-Next-Model.

cs.SE↗

arXiv2026

SONAR: Task-Aware Code Summary Evaluation for LLM Consumers Without References

Source code summaries have traditionally been evaluated from a human developer's perspective, with quality determined by how closely they resemble developer-written references and how well they align with human preferences. But this overlooks a growing reality: LLM-based tools and agents increasingly consume code summaries as inputs for software engineering (SE) tasks, and what makes a summary useful for a consuming agent on a task remains largely unexplored. To bridge this gap, we propose SONAR, a reference-free framework that evaluates source code summaries along four dimensions: Correctness, Abstraction, Conciseness, and Fluency. Rather than optimizing for a pre-written "gold standard", SONAR introduces a novel code regeneration-based approach that uses a summary to regenerate code and leverages that reconstruction as a quality signal of the summary. This provides an empirical grounding that requires neither a reference summary nor the subjective judgment of humans or LLMs. We evaluate SONAR's dimensions on their ability to influence LLM performance across four downstream SE tasks. We find that Correctness, followed by Abstraction, significantly correlates with LLM performance, with correlations up to 14X higher than the best baseline. Conciseness and Fluency, though widely valued by human developers, remain mostly insignificant to an LLM consumer, suggesting that what makes a summary useful is task- and consumer-dependent. Through a large-scale evaluation of 11 popular LLMs using SONAR, we further identify the strengths and weaknesses of different models across each quality dimension, while offering insights to facilitate future research on task-aware summarization.

cs.SE↗

arXiv2026

Documentation vs. Code Patterns: What Drives LLM-Based Exception Oracle Generation?

LLM-based test oracle generation (TOG) methods report high accuracy on exception oracle generation, but it remains unclear what evidence drives these predictions. In particular, do models use explicit exceptional-behavior documentation such as Javadoc @throws clauses, or do they rely on recurring patterns in tests, code, and documentation? We investigate this question through a large-scale intervention-based study of three TOG systems spanning classifier-based and generative architectures and model sizes from roughly 110M to 7B parameters, evaluated on three real-world benchmarks comprising two generated-test datasets and a new benchmark of developer-written tests. We first remove Javadoc @throws clauses and find that accuracy changes only marginally, with the largest drop below one percentage point. This indicates that structured exception documentation is not the primary driver of exception-oracle prediction. We then apply attribution-guided substitution ablations to identify the signals that predictions depend on. The results show that high accuracy can be driven by shortcut signals: some models are highly sensitive to a small number of structural tokens, while others distribute reliance across many lexical cues. These findings challenge the assumption that strong exception-oracle accuracy reflects robust use of exception semantics. Future TOG systems should therefore be evaluated not only by whether they predict the correct oracle type, but also by whether their predictions are grounded in meaningful exception-triggering evidence.

cs.SE↗

arXiv2026

PROGRESS: Property-Guided Regression Search for Semantic Falsification

Search-based regression-test generation effectively explores complex program structures, yielding high structural coverage, but its oracles are derived from the system under test: faults already present are recorded as expected behavior rather than exposed. Property-based testing offers independent semantic oracles, but depends on high-quality properties and gives little guidance for reaching deep states or satisfying selective preconditions. We present PROGRESS (PROperty-Guided REgression Search for Semantic Falsification), integrating intent-driven properties into coverage-guided, search-based evolutionary test generation to reach deep program states and detect violations of intended behavior. PROGRESS (1) extracts intent-bearing code context and uses a language-model pipeline to generate executable jqwik properties while limiting implementation leakage; (2) extends EvoSuite's DynaMOSA with a search objective and property-aware fitness function per property, rewarding progress through preconditions and prioritizing falsifying executions; and (3) binds property parameters and uses jqwik-provided generators to connect quantified inputs to evolving test sequences, steering generation toward coverage and bug-detection goals. We evaluate PROGRESS on 25 large-scale Java systems against regression-test generation, standalone property-based testing, and context ablations. PROGRESS detects 328/562 current-version bugs (58%) versus none for regression-test generation, and satisfies all preconditions for 70/150 hard-to-reach properties versus 18 for standalone jqwik. Ablations show documentation and caller/callee context are key to generating valid executable properties. PROGRESS preserves structural exploration while exposing faults missed by regression-derived assertions; we release a comprehensive artifact package.

cs.SE↗

arXiv2026

STADA: Specification-based Testing for Autonomous Driving Agents

Simulation-based testing has become a standard approach to validating autonomous driving agents prior to real-world deployment. A high-quality validation campaign will exercise an agent in diverse contexts comprised of varying static environments, e.g., lanes, intersections, signage, and dynamic elements, e.g., vehicles and pedestrians. To achieve this, existing test generation techniques rely on template-based, manually constructed, or random scenario generation. When applied to validate formally specified safety requirements, such methods either require significant human effort or run the risk of missing important behavior related to the requirement. To address this gap, we present STADA, a Specification-based Test generation framework for Autonomous Driving Agents that systematically generates the space of scenarios defined by a formal specification expressed in temporal logic (LTLf). Given a specification, STADA constructs all distinct initial scenes, a diverse space of continuations of those scenes, and simulations that reflect the behaviors of the specification. Evaluation of STADA on a variety of LTLf specifications formalized in SCENEFLOW using three complementary coverage criteria demonstrates that STADA yields more than 2x higher coverage than the best baseline on the finest criteria and a 75% increase for the coarsest criteria. Moreover, it matches the coverage of the best baseline with 6 times fewer simulations. While set in the context of autonomous driving, the approach is applicable to other domains with rich simulation environments.

cs.SE↗

arXiv2026

A Differential Fuzzing-Based Evaluation of Functional Equivalence in LLM-Generated Code Refactorings

With the rapid adoption of large language models (LLMs) in automated code refactoring, assessing and ensuring functional equivalence between LLM-generated refactoring and the original implementation becomes critical. While prior work typically relies on predefined test cases to evaluate correctness, in this work, we leverage differential fuzzing to check functional equivalence in LLM-generated code refactorings. Unlike test-based evaluation, a differential fuzzing-based equivalence checker needs no predefined test cases and can explore a much larger input space by executing and comparing thousands of automatically generated test inputs. In a large-scale evaluation of six LLMs (CodeLlama, Codestral, StarChat2, Qwen-2.5, Olmo-3, and GPT-4o) across three datasets and two refactoring types, we find that LLMs show a non-trivial tendency to alter program semantics, producing 19-35% functionally non-equivalent refactorings. Our experiments further demonstrate that about 21% of these non-equivalent refactorings remain undetected by the existing test suites of the three evaluated datasets. Collectively, the findings of this study imply that reliance on existing tests might overestimate functional equivalence in LLM-generated code refactorings, which remain prone to semantic divergence.

cs.SE↗

arXiv2026

LabelAny3D: Label Any Object 3D in the Wild

Detecting objects in 3D space from monocular input is crucial for applications ranging from robotics to scene understanding. Despite advanced performance in the indoor and autonomous driving domains, existing monocular 3D detection models struggle with in-the-wild images due to the lack of 3D in-the-wild datasets and the challenges of 3D annotation. We introduce LabelAny3D, an \emph{analysis-by-synthesis} framework that reconstructs holistic 3D scenes from 2D images to efficiently produce high-quality 3D bounding box annotations. Built on this pipeline, we present COCO3D, a new benchmark for open-vocabulary monocular 3D detection, derived from the MS-COCO dataset and covering a wide range of object categories absent from existing 3D datasets. Experiments show that annotations generated by LabelAny3D improve monocular 3D detection performance across multiple benchmarks, outperforming prior auto-labeling approaches in quality. These results demonstrate the promise of foundation-model-driven annotation for scaling up 3D recognition in realistic, open-world settings.

cs.CV↗

arXiv2025

Analyzing and Mitigating Surface Bias in Code Evaluation Metrics

With the increasing popularity of large language models (LLMs) and LLM-based agents, reliable and effective code evaluation metrics (CEMs) have become crucial for progress across several software engineering tasks. While popular benchmarks often provide test cases to assess the correctness of generated code, crafting and executing test cases is expensive. Reference-based CEMs provide a cheaper alternative by scoring a candidate program based on its functional similarity to a reference. Although prior research has focused on reporting the weak correlation between these CEMs and functional correctness, the causes are only assumed, and plausible solutions remain unexplored. In this work, we critically evaluate four state-of-the-art reference-based CEMs, revealing their strong bias towards surface-level features rather than code functionality. Despite this surface bias, current evaluation datasets for these CEMs rarely include code pairs that are surface-similar yet functionally dissimilar, or functionally similar yet surface-dissimilar. To mitigate this gap, we propose LoCaL (Looks Can Lie), a CEM evaluation benchmark, with 3117 code pairs at both the method and program levels. Each pair is labeled with a functional similarity score and aims to target regions where CEMs are likely to perform poorly. The functional similarity scores are calculated through differential fuzzing, which eliminates the need for predefined test cases and, at the same time, improves the reliability of the scores by executing an order of magnitude more tests than prior work. We find that all four CEMs show significant performance degradation on LoCaL, compared to the baselines. Finally, based on our findings, we draw the implication that exposing CEMs to LoCaL-like data might facilitate the development of metrics that are robust to surface bias.

cs.SE↗

arXiv2025

RBT4DNN: Requirements-based Testing of Neural Networks

Testing allows developers to determine whether a system functions as expected. When such systems include deep neural networks (DNNs), Testing becomes challenging, as DNNs approximate functions for which the formalization of functional requirements is intractable. This prevents the application of well-developed approaches to requirements-based testing to DNNs. To address this, we propose a requirements-based testing method (RBT4DNN) that uses natural language requirements statements. These statements use a glossary of terms to define a semantic feature space that can be leveraged for test input generation. RBT4DNN formalizes preconditions of functional requirements as logical combinations of those semantic features. Training data matching these feature combinations can be used to fine-tune a generative model to reliably produce test inputs satisfying the precondition. Executing these tests on a trained DNN enables comparing its output to the expected requirement postcondition behavior. We propose two use cases for RBT4DNN: (1) given requirements defining DNN correctness properties, RBT4DNN comprises a novel approach for detecting faults, and (2) during development, requirements-guided exploration of model behavior can provide developers with feedback on model generalization. Our further evaluation shows that RBT4DNN-generated tests are realistic, diverse, and aligned with requirement preconditions, enabling targeted analysis of model behavior and effective fault detection.

cs.SE↗

arXiv2025

Generating Realistic, Diverse, and Fault-Revealing Inputs with Latent Space Interpolation for Testing Deep Neural Networks

Deep Neural Networks (DNNs) have been widely employed across various domains, including safety-critical systems, necessitating comprehensive testing to ensure their reliability. Although numerous DNN model testing methods have been proposed to generate adversarial samples that are capable of revealing faults, existing methods typically perturb samples in the input space and then mutate these based on feedback from the DNN model. These methods often result in test samples that are not realistic and with low-probability reveal faults. To address these limitations, we propose a black-box DNN test input generation method, ARGUS, to generate realistic, diverse, and fault-revealing test inputs. ARGUS first compresses samples into a continuous latent space and then perturbs the original samples by interpolating these with samples of different classes. Subsequently, we employ a vector quantizer and decoder to reconstruct adversarial samples back into the input space. Additionally, we employ discriminators both in the latent space and in the input space to ensure the realism of the generated samples. Evaluation of ARGUS in comparison with state-of-the-art black-box testing and white-box testing methods, shows that ARGUS excels in generating realistic and diverse adversarial samples relative to the target dataset, and ARGUS successfully perturbs all original samples and achieves up to 4 times higher error rate than the best baseline method. Furthermore, using these adversarial samples for model retraining can improve model classification accuracy.

cs.LG↗

arXiv2024

Quantitative Predictive Monitoring and Control for Safe Human-Machine Interaction

There is a growing trend toward AI systems interacting with humans to revolutionize a range of application domains such as healthcare and transportation. However, unsafe human-machine interaction can lead to catastrophic failures. We propose a novel approach that predicts future states by accounting for the uncertainty of human interaction, monitors whether predictions satisfy or violate safety requirements, and adapts control actions based on the predictive monitoring results. Specifically, we develop a new quantitative predictive monitor based on Signal Temporal Logic with Uncertainty (STL-U) to compute a robustness degree interval, which indicates the extent to which a sequence of uncertain predictions satisfies or violates an STL-U requirement. We also develop a new loss function to guide the uncertainty calibration of Bayesian deep learning and a new adaptive control method, both of which leverage STL-U quantitative predictive monitoring results. We apply the proposed approach to two case studies: Type 1 Diabetes management and semi-autonomous driving. Experiments show that the proposed approach improves safety and effectiveness in both case studies.

cs.AI↗

arXiv2024

Measuring Feature Dependency of Neural Networks by Collapsing Feature Dimensions in the Data Manifold

This paper introduces a new technique to measure the feature dependency of neural network models. The motivation is to better understand a model by querying whether it is using information from human-understandable features, e.g., anatomical shape, volume, or image texture. Our method is based on the principle that if a model is dependent on a feature, then removal of that feature should significantly harm its performance. A targeted feature is "removed" by collapsing the dimension in the data distribution that corresponds to that feature. We perform this by moving data points along the feature dimension to a baseline feature value while staying on the data manifold, as estimated by a deep generative model. Then we observe how the model's performance changes on the modified test data set, with the target feature dimension removed. We test our method on deep neural network models trained on synthetic image data with known ground truth, an Alzheimer's disease prediction task using MRI and hippocampus segmentations from the OASIS-3 dataset, and a cell nuclei classification task using the Lizard dataset.

cs.LG↗

arXiv2024

Harnessing Neuron Stability to Improve DNN Verification

Deep Neural Networks (DNN) have emerged as an effective approach to tackling real-world problems. However, like human-written software, DNNs are susceptible to bugs and attacks. This has generated significant interests in developing effective and scalable DNN verification techniques and tools. In this paper, we present VeriStable, a novel extension of recently proposed DPLL-based constraint DNN verification approach. VeriStable leverages the insight that while neuron behavior may be non-linear across the entire DNN input space, at intermediate states computed during verification many neurons may be constrained to have linear behavior - these neurons are stable. Efficiently detecting stable neurons reduces combinatorial complexity without compromising the precision of abstractions. Moreover, the structure of clauses arising in DNN verification problems shares important characteristics with industrial SAT benchmarks. We adapt and incorporate multi-threading and restart optimizations targeting those characteristics to further optimize DPLL-based DNN verification. We evaluate the effectiveness of VeriStable across a range of challenging benchmarks including fully-connected feedforward networks (FNNs), convolutional neural networks (CNNs) and residual networks (ResNets) applied to the standard MNIST and CIFAR datasets. Preliminary results show that VeriStable is competitive and outperforms state-of-the-art DNN verification tools, including $α$-$β$-CROWN and MN-BaB, the first and second performers of the VNN-COMP, respectively.

cs.LG↗

arXiv2023

Neural-Based Test Oracle Generation: A Large-scale Evaluation and Lessons Learned

Defining test oracles is crucial and central to test development, but manual construction of oracles is expensive. While recent neural-based automated test oracle generation techniques have shown promise, their real-world effectiveness remains a compelling question requiring further exploration and understanding. This paper investigates the effectiveness of TOGA, a recently developed neural-based method for automatic test oracle generation by Dinella et al. TOGA utilizes EvoSuite-generated test inputs and generates both exception and assertion oracles. In a Defects4j study, TOGA outperformed specification, search, and neural-based techniques, detecting 57 bugs, including 30 unique bugs not detected by other methods. To gain a deeper understanding of its applicability in real-world settings, we conducted a series of external, extended, and conceptual replication studies of TOGA. In a large-scale study involving 25 real-world Java systems, 223.5K test cases, and 51K injected faults, we evaluate TOGA's ability to improve fault-detection effectiveness relative to the state-of-the-practice and the state-of-the-art. We find that TOGA misclassifies the type of oracle needed 24% of the time and that when it classifies correctly around 62% of the time it is not confident enough to generate any assertion oracle. When it does generate an assertion oracle, more than 47% of them are false positives, and the true positive assertions only increase fault detection by 0.3% relative to prior work. These findings expose limitations of the state-of-the-art neural-based oracle generation technique, provide valuable insights for improvement, and offer lessons for evaluating future automated oracle generation methods.

cs.SE↗

arXiv2023

Artifact: Measuring and Mitigating Gaps in Structural Testing

The artifact used for evaluating the experimental results of Measuring and Mitigating Gaps in Structural Testing is publicly available on GitHub, Software Heritage and figshare, and is reusable. The artifact consists of necessary data, tools, scripts, and detailed documentation for running the experiments and reproducing the results shown in the paper. We have also provided a VirtualBox VM image allowing users to quickly setup and reproduce the results. Users are expected to be familiar using the VirtualBox software and Linux platform for evaluating or reusing the artifact.

cs.SE↗