Searcharxiv⌕ Search

arXiv subjects

Mingyi Zhou

Publications and source records attributed to Mingyi Zhou.

At least 19 recordsLinked to original sources
arXiv2026

An Empirical Study for Android-to-OpenHarmony GUI Test Migration

To reduce the substantial engineering effort required to test the corresponding applications from Android to OpenHarmony, migrating existing GUI test cases has become a critical problem. However, current research neither proposes solutions tailored for OpenHarmony nor provides a systematic evaluation of migration approaches on this system, leaving developers with limited empirical guidance in practice. In this paper, we present the first systematic empirical study of test migration from Android to OpenHarmony. Specifically, we first construct a dataset referred to as the ATH Benchmark, comprising 36 commercial applications with an average of over 9 billion downloads, along with 108 manually designed test cases. Second, we select two state-of-the-art test migration approaches (i.e., ReSPlay and ITeM) and adapt these two approaches to enable their execution on OpenHarmony. Third, we use the preceding infrastructure to evaluate these two approaches from three perspectives, including testing performance, root causes of failures, and the impact of OpenHarmony characteristics. Our results reveal that existing test migration approaches are less effective (15% success-rate on ReSPlay and 26% success-rate on ITeM) in Android-to-OpenHarmony scenarios. Through an in-depth analysis of failed cases, we identify that test performance is primarily hindered by OpenHarmony-specific characteristics, including technical architecture differences and unique ecosystem traits. Utilizing these findings, we propose an enhanced approach based on ITeM, referred as ITeM-HM, which incorporates specific OpenHarmony system features. As a result, ITeM-HM successfully achieves a 214% success-rate relative improvement over the original ITeM (from 26% to 81%).

cs.SE↗
arXiv2026

AtomicCommitBench: Can Coding Agents Reconstruct Commit Histories from Squashed Patches?

Coding agents often finish a session by returning one squashed patch that mixes feature implementation, bug fixes, refactorings, tests, and configuration edits. While the final code may be correct, collapsing unrelated edits into one patch removes the history structure needed for review, selective revert, and later maintenance. We study retrospective commit-history reconstruction: given a completed squashed change, an agent groups its hunks into commits and materializes a replayable commit sequence. We formalize the task as hunk-to-commit partitioning with a replay requirement and build AtomicCommitBench, containing 800 real consecutive-commit episodes from 10 Python projects. Because multiple decompositions may be reasonable, we evaluate outputs using complementary metrics: PPAR for replay validity, ARI for reference-based grouping quality, and TCR for failure containment on scoreable modified-test episodes. Natural retrospective reconstruction proves substantially harder than replay checking or synthetic tangling. Although nearly all non-random methods achieve replay validity (PPAR >= 0.988), grouping quality ranges from 0.03 to 0.46 ARI. Matched synthetic composites are much easier than real same-author squashed diffs (+0.333 ARI). In our evaluation, the GPT-5.4 setup driven by Codex CLI (0.46 ARI) and the GLM-5 setup driven by Claude Code (0.43 ARI) outperform MiniMax (0.31) and Kimi (0.29). Qualitative analysis identifies same-file lumping and support-hunk drift as recurring failure modes. Dependency-Aware Commit Evidence (DACE) improves the lower-scoring setups by 0.05 to 0.08 ARI, indicating that dependency cues and hunk-role information help agents avoid locality-driven grouping errors. AtomicCommitBench enables evaluation of the commit histories produced by coding agents alongside the final code.

cs.SE↗
arXiv2026

RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue

Open-source libraries and tools are widely reused, but compatibility maintenance is expensive. Once maintainers leave, useful repositories can stop working as runtimes and dependencies evolve. We study whether LLM agents can adapt old repositories to modern environments, a task we call compatibility rescue. Unlike bug repair, compatibility rescue starts from a repository that worked in its original environment but fails after ecosystem drift. RepoRescue gives agents only the repository and its failing modern environment; the agent must diagnose the failure, locate affected code, and produce a source-code rescue that restores the historical test suite. We build RepoRescue from 193 Python and 122 Java repositories, each verified to pass historically and fail after modernization. We evaluate five deployed agent systems on Python and three on Java. Beyond full-patch pass rate, we rerun patches after removing test-file edits to measure source-only repair, add a runtime-enforced regime that blocks test edits, and validate practical use for repositories whose suites pass after rescue. We find that Claude Code systems sometimes edit failing tests even when prompted not to; with runtime blocking, Kimi still rescues 41.5% of repositories. Systems are complementary: their union reaches 62.7%, exceeding the best single system by 10.9 points. Difficulty concentrates in cross-file coordination: on 14 repositories requiring coordinated whole-codebase changes, GPT-5.2 through Codex passes all 14, while every Claude Code system passes at most two. Finally, a passing suite is only an initial signal: among 34 unmaintained Python candidates whose suites pass after rescue, 22 work in realistic scenarios and 12 pass bug-hunt with patches that address the compatibility failure. RepoRescue benchmarks compatibility rescue with source-only auditing, runtime enforcement, practical validation, and reasoning labels.

cs.SE↗
arXiv2026

To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair

LLM-based agents for program repair are increasingly built on a "generate-run-revise" paradigm, iteratively executing tests to evaluate and refine patches. This execution-based approach has become standard practice in state-of-the-art systems. However, executions can be time-consuming and expensive, yet their impact on these agents remains underexplored. In this paper, we conduct a two-stage empirical study over execution behavior in LLM-based program repair. To characterize execution behavior at scale, we first analyze 7,745 agent traces from SWE-bench leaderboard submissions. Second, we evaluate 3,000 end-to-end repair attempts across 200 SWE-bench instances and three agents (Claude Code, Codex, and the open-source OpenCode) under four execution paradigms, which allows for a fine-grained comparison of performance and cost. Our analysis reveals three key observations: (1) Code execution is used across all agents and models analyzed, with an average of 8.8 test runs per task. Execution behavior varies substantially across agents and models, with frequency ranging from 2 to 19 per task, and late-stage executions consistently achieve higher success rates than early-stage ones. (2) Execution restrictions have little effect on repair success: on commercial agents with SOTA models the resolve-rate gap between Prohibited and Unrestricted is only 1.25 percentage points and not statistically significant, while Prohibited saves substantial token and wall-clock cost. (3) Execution benefit is concentrated rather than uniform. These patterns suggest that current agents apply execution indiscriminately, paying its cost on instances where it provides little benefit. Execution, therefore, should be treated as a resource with an explicit cost-benefit tradeoff, not a default capability.

cs.SE↗
arXiv2026

How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring

LLM-based code agents navigate repositories through keyword search but miss the structural relationships, such as call graphs, inheritance hierarchies, and configuration dependencies, that define how software actually works. This makes agent navigation stochastic and difficult to reproduce across runs. We investigate whether lightweight static analysis can provide deterministic anchors for these agents: stable structural facts injected as plain-text comments that constrain probabilistic exploration and make navigation more predictable. Starting from a strong baseline, Codex from OpenAI, we systematically inject varying granularities of structural annotations and measure their effects on localization, trajectory behavior, and run-to-run stability. Our study identifies what we call the deterministic anchoring effect: static structure helps less by making agents "smarter" and more by making their navigation disciplined and reproducible. Three observations support this finding: (1) Anchoring works: lightweight call/inheritance topology improves function-level localization (+2.2pp Func@5) and shortens trajectories (-1.6 interaction rounds); (2) Anchoring is scale-sensitive: the optimal granularity and directionality depend on repository characteristics, where denser semantics show diminishing returns and hub-heavy projects benefit from inverse-only links that expose "who-calls-me" without forward edges; (3) Anchoring stabilizes: tags raise link-following rate from 0.15-0.18 to 0.21-0.24, roughly halve run-to-run variance, and improve single-run reliability (Pass@1 +3.4 pp) on medium-scale repositories, at the cost of roughly 10% more input tokens. These observations suggest practical guidelines: default to lightweight topology on medium projects, prune forward edges in large repositories, and reserve dense tags for implicit-dependency cases.

cs.SE↗
arXiv2026

Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters

Current LLM systems are increasingly equipped with a code interpreter that executes generated code to obtain results. This works serially: the model first generates the complete code, then an interpreter executes it. This sequential workflow leaves the executor idle during generation and the generator idle during execution, resulting in unnecessary end-to-end latency. Our key observation is that an LLM, unlike a human developer, emits code tokens left to right and does not backtrack over what it has already written. This makes it possible to start executing a piece of code while later tokens are still being generated. We formalize this parallel execution paradigm, modeling it as a three-stage pipeline of generation, detection, and execution, and derive closed-form latency bounds that characterize its speedup potential and operating regimes. We then present EAGER, a concrete implementation featuring AST-based chunking, dynamic batching with gated execution, and early error interruption. We evaluate EAGER across four benchmarks, seven LLMs, and three execution environments. The overlap mechanism hides almost all execution behind generation, reducing the non-overlapped portion of execution time by up to 99.8% and cutting end-to-end latency by up to 37.3% on error-free runs.

cs.PL↗
arXiv2026

Context-Sensitive Pointer Analysis for ArkTS

Current call graph generation methods for ArkTS, a new programming language for OpenHarmony, exhibit precision limitations when supporting advanced static analysis tasks such as data flow analysis and vulnerability pattern detection, while the workflow of traditional JavaScript(JS)/TypeScript(TS) analysis tools fails to interpret ArkUI component tree semantics. The core technical bottleneck originates from the closure mechanisms inherent in TypeScript's dynamic language features and the interaction patterns involving OpenHarmony's framework APIs. Existing static analysis tools for ArkTS struggle to achieve effective tracking and precise deduction of object reference relationships, leading to topological fractures in call graph reachability and diminished analysis coverage. This technical limitation fundamentally constrains the implementation of advanced program analysis techniques. Therefore, in this paper, we propose a tool named ArkAnalyzer Pointer Analysis Kit (APAK), the first context-sensitive pointer analysis framework specifically designed for ArkTS. APAK addresses these challenges through a unique ArkTS heap object model and a highly extensible plugin architecture, ensuring future adaptability to the evolving OpenHarmony ecosystem. In the evaluation, we construct a dataset from 1,663 real-world applications in the OpenHarmony ecosystem to evaluate APAK, demonstrating APAK's superior performance over CHA/RTA approaches in critical metrics including valid edge coverage (e.g., a 7.1% reduction compared to CHA and a 34.2% increase over RTA). The improvement in edge coverage systematically reduces false positive rates from 20% to 2%, enabling future exploration of establishing more complex program analysis tools based on our framework. Our proposed APAK has been merged into the official static analysis framework ArkAnalyzer for OpenHarmony.

cs.SE↗
arXiv2025

IMU: Influence-guided Machine Unlearning

Machine Unlearning (MU) aims to selectively erase the influence of specific data points from pretrained models. However, most existing MU methods rely on the retain set to preserve model utility, which is often impractical due to privacy restrictions and storage constraints. While several retain-data-free methods attempt to bypass this using geometric feature shifts or auxiliary statistics, they typically treat forgetting samples uniformly, overlooking their heterogeneous contributions. To address this, we propose \ul{I}nfluence-guided \ul{M}achine \ul{U}nlearning (IMU), a principled method that conducts MU using only the forget set. Departing from uniform Gradient Ascent (GA) or implicit weighting mechanisms, IMU leverages influence functions as an explicit priority signal to allocate unlearning strength. To circumvent the prohibitive cost of full-model Hessian inversion, we introduce a theoretically grounded classifier-level influence approximation. This efficient design allows IMU to dynamically reweight unlearning updates, aggressively targeting samples that most strongly support the forgetting objective while minimizing unnecessary perturbation to retained knowledge. Extensive experiments across vision and language tasks show that IMU achieves highly competitive results. Compared to standard uniform GA, IMU maintains identical unlearning depth while enhancing model utility by an average of 30%, effectively overcoming the inherent utility-forgetting trade-off.

cs.LG↗
arXiv2025

Privacy Protection Against Personalized Text-to-Image Synthesis via Cross-image Consistency Constraints

The rapid advancement of diffusion models and personalization techniques has made it possible to recreate individual portraits from just a few publicly available images. While such capabilities empower various creative applications, they also introduce serious privacy concerns, as adversaries can exploit them to generate highly realistic impersonations. To counter these threats, anti-personalization methods have been proposed, which add adversarial perturbations to published images to disrupt the training of personalization models. However, existing approaches largely overlook the intrinsic multi-image nature of personalization and instead adopt a naive strategy of applying perturbations independently, as commonly done in single-image settings. This neglects the opportunity to leverage inter-image relationships for stronger privacy protection. Therefore, we advocate for a group-level perspective on privacy protection against personalization. Specifically, we introduce Cross-image Anti-Personalization (CAP), a novel framework that enhances resistance to personalization by enforcing style consistency across perturbed images. Furthermore, we develop a dynamic ratio adjustment strategy that adaptively balances the impact of the consistency loss throughout the attack iterations. Extensive experiments on the classical CelebHQ and VGGFace2 benchmarks show that CAP substantially improves existing methods.

cs.CV↗
arXiv2025

ArkAnalyzer: The Static Analysis Framework for OpenHarmony

ArkTS is a new programming language dedicated to developing apps for the emerging OpenHarmony mobile operating system. Like other programming languages constantly suffering from performance-related code smells or vulnerabilities, the ArkTS programming language will likely encounter the same problems. The solution given by our research community is to invent static analyzers, which are often implemented on top of a common static analysis framework, to detect and subsequently repair those issues automatically. Unfortunately, such an essential framework is not available for the OpenHarmony community yet. Existing program analysis methods have several problems when handling the ArkTS code. To bridge the gap, we design and implement a framework named ArkAnalyzer and make it publicly available as an open-source project. Our ArkAnalyzer addresses the aforementioned problems and has already integrated a number of fundamental static analysis functions that are ready to be reused by developers to implement OpenHarmony

cs.SE↗
arXiv2024

DynaMO: Protecting Mobile DL Models through Coupling Obfuscated DL Operators

Deploying DL models on mobile Apps has become ever-more popular. However, existing studies show attackers can easily reverse-engineer mobile DL models in Apps to steal intellectual property or generate effective attacks. A recent approach, Model Obfuscation, has been proposed to defend against such reverse engineering by obfuscating DL model representations, such as weights and computational graphs, without affecting model performance. These existing model obfuscation methods use static methods to obfuscate the model representation, or they use half-dynamic methods but require users to restore the model information through additional input arguments. However, these static methods or half-dynamic methods cannot provide enough protection for on-device DL models. Attackers can use dynamic analysis to mine the sensitive information in the inference codes as the correct model information and intermediate results must be recovered at runtime for static and half-dynamic obfuscation methods. We assess the vulnerability of the existing obfuscation strategies using an instrumentation method and tool, DLModelExplorer, that dynamically extracts correct sensitive model information at runtime. Experiments show it achieves very high attack performance. To defend against such attacks based on dynamic instrumentation, we propose DynaMO, a Dynamic Model Obfuscation strategy similar to Homomorphic Encryption. The obfuscation and recovery process can be done through simple linear transformation for the weights of randomly coupled eligible operators, which is a fully dynamic obfuscation strategy. Experiments show that our proposed strategy can dramatically improve model security compared with the existing obfuscation strategies, with only negligible overheads for on-device models.

cs.SE↗
arXiv2024

PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach

In recent years, Large Language Models (LLMs) have gained widespread use, raising concerns about their security. Traditional jailbreak attacks, which often rely on the model internal information or have limitations when exploring the unsafe behavior of the victim model, limiting their reducing their general applicability. In this paper, we introduce PathSeeker, a novel black-box jailbreak method, which is inspired by the game of rats escaping a maze. We think that each LLM has its unique "security maze", and attackers attempt to find the exit learning from the received feedback and their accumulated experience to compromise the target LLM's security defences. Our approach leverages multi-agent reinforcement learning, where smaller models collaborate to guide the main LLM in performing mutation operations to achieve the attack objectives. By progressively modifying inputs based on the model's feedback, our system induces richer, harmful responses. During our manual attempts to perform jailbreak attacks, we found that the vocabulary of the response of the target model gradually became richer and eventually produced harmful responses. Based on the observation, we also introduce a reward mechanism that exploits the expansion of vocabulary richness in LLM responses to weaken security constraints. Our method outperforms five state-of-the-art attack techniques when tested across 13 commercial and open-source LLMs, achieving high attack success rates, especially in strongly aligned commercial models like GPT-4o-mini, Claude-3.5, and GLM-4-air with strong safety alignment. This study aims to improve the understanding of LLM security vulnerabilities and we hope that this sturdy can contribute to the development of more robust defenses.

cs.CR↗
arXiv2024

LLM for Mobile: An Initial Roadmap

When mobile meets LLMs, mobile app users deserve to have more intelligent usage experiences. For this to happen, we argue that there is a strong need to appl LLMs for the mobile ecosystem. We therefore provide a research roadmap for guiding our fellow researchers to achieve that as a whole. In this roadmap, we sum up six directions that we believe are urgently required for research to enable native intelligence in mobile devices. In each direction, we further summarize the current research progress and the gaps that still need to be filled by our fellow researchers.

cs.SE↗
arXiv2024

Model-less Is the Best Model: Generating Pure Code Implementations to Replace On-Device DL Models

Recent studies show that deployed deep learning (DL) models such as those of Tensor Flow Lite (TFLite) can be easily extracted from real-world applications and devices by attackers to generate many kinds of attacks like adversarial attacks. Although securing deployed on-device DL models has gained increasing attention, no existing methods can fully prevent the aforementioned threats. Traditional software protection techniques have been widely explored, if on-device models can be implemented using pure code, such as C++, it will open the possibility of reusing existing software protection techniques. However, due to the complexity of DL models, there is no automatic method that can translate the DL models to pure code. To fill this gap, we propose a novel method, CustomDLCoder, to automatically extract the on-device model information and synthesize a customized executable program for a wide range of DL models. CustomDLCoder first parses the DL model, extracts its backend computing units, configures the computing units to a graph, and then generates customized code to implement and deploy the ML solution without explicit model representation. The synthesized program hides model information for DL deployment environments since it does not need to retain explicit model representation, preventing many attacks on the DL model. In addition, it improves ML performance because the customized code removes model parsing and preprocessing steps and only retains the data computing process. Our experimental results show that CustomDLCoder improves model security by disabling on-device model sniffing. Compared with the original on-device platform (i.e., TFLite), our method can accelerate model inference by 21.8% and 24.3% on x86-64 and ARM64 platforms, respectively. Most importantly, it can significantly reduce memory consumption by 68.8% and 36.0% on x86-64 and ARM64 platforms, respectively.

cs.SE↗
arXiv2024

Investigating White-Box Attacks for On-Device Models

Numerous mobile apps have leveraged deep learning capabilities. However, on-device models are vulnerable to attacks as they can be easily extracted from their corresponding mobile apps. Existing on-device attacking approaches only generate black-box attacks, which are far less effective and efficient than white-box strategies. This is because mobile deep learning frameworks like TFLite do not support gradient computing, which is necessary for white-box attacking algorithms. Thus, we argue that existing findings may underestimate the harmfulness of on-device attacks. To this end, we conduct a study to answer this research question: Can on-device models be directly attacked via white-box strategies? We first systematically analyze the difficulties of transforming the on-device model to its debuggable version, and propose a Reverse Engineering framework for On-device Models (REOM), which automatically reverses the compiled on-device TFLite model to the debuggable model. Specifically, REOM first transforms compiled on-device models into Open Neural Network Exchange format, then removes the non-debuggable parts, and converts them to the debuggable DL models format that allows attackers to exploit in a white-box setting. Our experimental results show that our approach is effective in achieving automated transformation among 244 TFLite models. Compared with previous attacks using surrogate models, REOM enables attackers to achieve higher attack success rates with a hundred times smaller attack perturbations. In addition, because the ONNX platform has plenty of tools for model format exchanging, the proposed method based on the ONNX platform can be adapted to other model formats. Our findings emphasize the need for developers to carefully consider their model deployment strategies, and use white-box methods to evaluate the vulnerability of on-device models.

cs.SE↗
arXiv2023

Concealing Sensitive Samples against Gradient Leakage in Federated Learning

Federated Learning (FL) is a distributed learning paradigm that enhances users privacy by eliminating the need for clients to share raw, private data with the server. Despite the success, recent studies expose the vulnerability of FL to model inversion attacks, where adversaries reconstruct users private data via eavesdropping on the shared gradient information. We hypothesize that a key factor in the success of such attacks is the low entanglement among gradients per data within the batch during stochastic optimization. This creates a vulnerability that an adversary can exploit to reconstruct the sensitive data. Building upon this insight, we present a simple, yet effective defense strategy that obfuscates the gradients of the sensitive data with concealed samples. To achieve this, we propose synthesizing concealed samples to mimic the sensitive data at the gradient level while ensuring their visual dissimilarity from the actual sensitive data. Compared to the previous art, our empirical evaluations suggest that the proposed technique provides the strongest protection while simultaneously maintaining the FL performance.

cs.LG↗
arXiv2023

ModelObfuscator: Obfuscating Model Information to Protect Deployed ML-based Systems

More and more edge devices and mobile apps are leveraging deep learning (DL) capabilities. Deploying such models on devices -- referred to as on-device models -- rather than as remote cloud-hosted services, has gained popularity because it avoids transmitting user data off of the device and achieves high response time. However, on-device models can be easily attacked, as they can be accessed by unpacking corresponding apps and the model is fully exposed to attackers. Recent studies show that attackers can easily generate white-box-like attacks for an on-device model or even inverse its training data. To protect on-device models from white-box attacks, we propose a novel technique called model obfuscation. Specifically, model obfuscation hides and obfuscates the key information -- structure, parameters and attributes -- of models by renaming, parameter encapsulation, neural structure obfuscation obfuscation, shortcut injection, and extra layer injection. We have developed a prototype tool ModelObfuscator to automatically obfuscate on-device TFLite models. Our experiments show that this proposed approach can dramatically improve model security by significantly increasing the difficulty of parsing models inner information, without increasing the latency of DL models. Our proposed on-device model obfuscation has the potential to be a fundamental technique for on-device model deployment. Our prototype tool is publicly available at: https://github.com/zhoumingyi/ModelObfuscator.

cs.CR↗
arXiv2023

Local Label Point Correction for Edge Detection of Overlapping Cervical Cells

Accurate labeling is essential for supervised deep learning methods. However, it is almost impossible to accurately and manually annotate thousands of images, which results in many labeling errors for most datasets. We proposes a local label point correction (LLPC) method to improve annotation quality for edge detection and image segmentation tasks. Our algorithm contains three steps: gradient-guided point correction, point interpolation and local point smoothing. We correct the labels of object contours by moving the annotated points to the pixel gradient peaks. This can improve the edge localization accuracy, but it also causes unsmooth contours due to the interference of image noise. Therefore, we design a point smoothing method based on local linear fitting to smooth the corrected edge. To verify the effectiveness of our LLPC, we construct a largest overlapping cervical cell edge detection dataset (CCEDD) with higher precision label corrected by our label correction method. Our LLPC only needs to set three parameters, but yields 30-40$\%$ average precision improvement on multiple networks. The qualitative and quantitative experimental results show that our LLPC can improve the quality of manual labels and the accuracy of overlapping cell edge detection. We hope that our study will give a strong boost to the development of the label correction for edge detection and image segmentation. We will release the dataset and code at https://github.com/nachifur/LLPC.

cs.CV↗