arXiv subjects

Zibin Zheng

Publications and source records attributed to Zibin Zheng.

At least 73 records · Page 4Linked to original sources

arXiv2026

LogPrism: Unifying Structure and Variable Encoding for Effective Log Compression

In the field of log compression, the prevailing "parse-then-compress" paradigm fundamentally limits effectiveness by treating log parsing and compression as isolated objectives. While parsers prioritize semantic accuracy (i.e., event identification), they often obscure deep correlations between static templates and dynamic variables that are critical for storage efficiency. In this paper, we investigate this misalignment through a comprehensive empirical study and propose LogPrism, a framework that bridges the gap via unified redundancy encoding. Rather than relying on a rigid pre-parsing step, LogPrism dynamically integrates structural extraction with variable encoding by constructing a Unified Redundancy Tree (URT). This hierarchical approach effectively mines "structure+variable" co-occurrence patterns, capturing deep contextual redundancies while accelerating processing through pre-emptive pattern encoding. Extensive experiments on 16 benchmark datasets confirm that LogPrism establishes a new state-of-the-art. It achieves the highest compression ratio on 14 datasets, surpassing existing baselines by margins of 6.12% to 83.34%, while delivering superior throughput at 29.87 MB/s (1.68$\times$~43.04$\times$ faster than competitors). Moreover, when configured in single-archive mode to maximize global pattern discovery, LogPrism boosts its compression ratio by 273.27%, outperforming the best baseline by 19.39% with a 2.62$\times$ speed advantage.

cs.SE↗

arXiv2026

DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning

Large language models (LLMs) have demonstrated impressive capabilities in code generation by leveraging retrieval-augmented generation (RAG) methods. However, the computational costs associated with LLM inference, particularly in terms of latency and energy consumption, have received limited attention in the security context. This paper introduces DrainCode, the first adversarial attack targeting the computational efficiency of RAG-based code generation systems. By strategically poisoning retrieval contexts through a mutation-based approach, DrainCode forces LLMs to produce significantly longer outputs, thereby increasing GPU latency and energy consumption. We evaluate the effectiveness of DrainCode across multiple models. Our experiments show that DrainCode achieves up to an 85% increase in latency, a 49% increase in energy consumption, and more than a 3x increase in output length compared to the baseline. Furthermore, we demonstrate the generalizability of the attack across different prompting strategies and its effectiveness compared to different defenses. The results highlight DrainCode as a potential method for increasing the computational overhead of LLMs, making it useful for evaluating LLM security in resource-constrained environments. We provide code and data at https://github.com/DeepSoftwareAnalytics/DrainCode.

cs.SE↗

arXiv2026

Cast: Automated Resilience Testing for Production Cloud Service Systems

The distributed nature of microservice architecture introduces significant resilience challenges. Traditional testing methods, limited by extensive manual effort and oversimplified test environments, fail to capture production system complexity. To address these limitations, we present Cast, an automated, end-to-end framework for microservice resilience testing in production. It achieves high test fidelity by replaying production traffic against a comprehensive library of application-level faults to exercise internal error-handling logic. To manage the combinatorial test space, Cast employs a complexity-driven strategy to systematically prune redundant tests and prioritize high-value tests targeting the most critical service execution paths. Cast automates the testing lifecycle through a three-phase pipeline (i.e., startup, fault injection, and recovery) and uses a multi-faceted oracle to automatically verify system resilience against nuanced criteria. Deployed in Huawei Cloud for over eight months, Cast has been adopted by many service teams to proactively address resilience vulnerabilities. Our analysis on four large-scale applications with millions of traces reveals 137 potential vulnerabilities, with 89 confirmed by developers. To further quantify its performance, Cast is evaluated on a benchmark set of 48 reproduced bugs, achieving a high coverage of 90%. The results show that Cast is a practical and effective solution for systematically improving the reliability of industrial microservice systems.

cs.SE↗

arXiv2026

RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories

Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area. Existing benchmarks often fall short by relying on synthetic vulnerabilities or evaluating functional correctness in isolation, failing to capture the complex interplay between functionality and security found in real-world software. To address this gap, we introduce RealSec-bench, a new benchmark for secure code generation meticulously constructed from real-world, high-risk Java repositories. Our methodology employs a multi-stage pipeline that combines systematic SAST scanning with CodeQL, LLM-based false positive elimination, and rigorous human expert validation. The resulting benchmark contains 105 instances grounded in real-word repository contexts, spanning 19 Common Weakness Enumeration (CWE) types and exhibiting a wide diversity of data flow complexities, including vulnerabilities with up to 34-hop inter-procedural dependencies. Using RealSec-bench, we conduct an extensive empirical study on 5 popular LLMs. We introduce a novel composite metric, SecurePass@K, to assess both functional correctness and security simultaneously. We find that while Retrieval-Augmented Generation (RAG) techniques can improve functional correctness, they provide negligible benefits to security. Furthermore, explicitly prompting models with general security guidelines often leads to compilation failures, harming functional correctness without reliably preventing vulnerabilities. Our work highlights the gap between functional and secure code generation in current LLMs.

cs.CR↗

arXiv2026

Is My RPC Response Reliable? Detecting RPC Bugs in Ethereum Blockchain Client under Context

Blockchain clients are fundamental software for running blockchain nodes. They provide users with various RPC (Remote Procedure Call) interfaces to interact with the blockchain. These RPC methods are expected to follow the same specification across different blockchain nodes, providing users with seamless interaction. However, there have been continuous reports on various RPC bugs that can cause unexpected responses or even Denial of Service weakness. Existing studies on blockchain RPC bug detection mainly focus on generating the RPC method calls for testing blockchain clients. However, a wide range of the reported RPC bugs are triggered in various blockchain contexts. To the best of our knowledge, little attention is paid to generating proper contexts that can trigger these context-dependent RPC bugs. In this work, we propose EthCRAFT, a Context-aware RPC Analysis and Fuzzing Tool for client RPC bug detection. EthCRAFT first proposes to explore the state transition program space of blockchain clients and generate various transactions to construct the context. EthCRAFT then designs a context-aware RPC method call generation method to send RPC calls to the blockchain clients. The responses of 5 different client implementations are used as cross-referring oracles to detect the RPC bugs. We evaluate EthCRAFT on real-world RPC bugs collected from the GitHub issues of Ethereum client implementations. Experiment results show that EthCRAFT outperforms existing client RPC detectors by detecting more RPC bugs. Moreover, EthCRAFT has found six new bugs in major Ethereum clients and reported them to the developers. One of the bug fixes has been written into breaking changes in the client's updates. Three of our bug reports have been offered a vulnerability bounty by the Ethereum Foundation.

cs.SE↗

arXiv2026

DemoTuner: Automatic Performance Tuning for Database Management Systems Based on Demonstration Reinforcement Learning

The performance of modern DBMSs such as MySQL and PostgreSQL heavily depends on the configuration of performance-critical knobs. Manual tuning these knobs is laborious and inefficient due to the complex and high-dimensional nature of the configuration space. Among the automated tuning methods, reinforcement learning (RL)-based methods have recently sought to improve the DBMS knobs tuning process from several different perspectives. However, they still encounter challenges with slow convergence speed during offline training. In this paper, we mainly focus on how to leverage the valuable tuning hints contained in various textual documents such as DBMS manuals and web forums to improve the offline training of RL-based methods. To this end, we propose an efficient DBMS knobs tuning framework named DemoTuner via a novel LLM-assisted demonstration reinforcement learning method. Specifically, to comprehensively and accurately mine tuning hints from documents, we design a structured chain of thought prompt to employ LLMs to conduct a condition-aware tuning hints extraction task. To effectively integrate the mined tuning hints into RL agent training, we propose a hint-aware demonstration reinforcement learning algorithm HA-DDPGfD in DemoTuner. As far as we know, DemoTuner is the first work to introduce the demonstration reinforcement learning algorithm for DBMS knobs tuning. Experimental evaluations conducted on MySQL and PostgreSQL across various workloads demonstrate that DemoTuner achieves performance gains of up to 44.01% for MySQL and 39.95% for PostgreSQL over default configurations. Compared with three representative baseline methods, DemoTuner is able to further reduce the execution time by up to 10.03%, while always consuming the least online tuning cost. Additionally, DemoTuner also exhibits superior adaptability to application scenarios with unknown workloads.

cs.LG↗

arXiv2026

Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey

Issue resolution, a complex Software Engineering (SWE) task integral to real-world development, has emerged as a compelling challenge for artificial intelligence. The establishment of benchmarks like SWE-bench revealed this task as profoundly difficult for large language models, thereby significantly accelerating the evolution of autonomous coding agents. This paper presents a systematic survey of this emerging domain. We begin by examining data construction pipelines, covering automated collection and synthesis approaches. We then provide a comprehensive analysis of methodologies, spanning training-free frameworks with their modular components to training-based techniques, including supervised fine-tuning and reinforcement learning. Subsequently, we discuss critical analyses of data quality and agent behavior, alongside practical applications. Finally, we identify key challenges and outline promising directions for future research. An open-source repository is maintained at https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution to serve as a dynamic resource in this field.

cs.SE↗

arXiv2026

SSR: Safeguarding Staking Rewards by Defining and Detecting Logical Defects in DeFi Staking

Decentralized Finance (DeFi) staking is one of the most prominent applications within the DeFi ecosystem, where DeFi projects enable users to stake tokens on the platform and reward participants with additional tokens. However, logical defects in DeFi staking could enable attackers to claim unwarranted rewards by manipulating reward amounts, repeatedly claiming rewards, or engaging in other malicious actions. To mitigate these threats, we conducted the first study focused on defining and detecting logical defects in DeFi staking. Through the analysis of 64 security incidents and 144 audit reports, we identified six distinct types of logical defects, each accompanied by detailed descriptions and code examples. Building on this empirical research, we developed SSR (Safeguarding Staking Reward), a static analysis tool designed to detect logical defects in DeFi staking contracts. SSR utilizes a large language model (LLM) to extract fundamental information about staking logic and constructs a DeFi staking model. It then identifies logical defects by analyzing the model and the associated semantic features. We constructed a ground truth dataset based on known security incidents and audit reports to evaluate the effectiveness of SSR. The results indicate that SSR achieves an overall precision of 92.31%, a recall of 87.92%, and an F1-score of 88.85%. Additionally, to assess the prevalence of logical defects in real-world smart contracts, we compiled a large-scale dataset of 15,992 DeFi staking contracts. SSR detected that 3,557 (22.24%) of these contracts contained at least one logical defect.

cs.SE↗

arXiv2026

A Survey on Failure Analysis and Fault Injection in AI Systems

The rapid advancement of Artificial Intelligence (AI) has led to its integration into various areas, especially with Large Language Models (LLMs) significantly enhancing capabilities in Artificial Intelligence Generated Content (AIGC). However, the complexity of AI systems has also exposed their vulnerabilities, necessitating robust methods for failure analysis (FA) and fault injection (FI) to ensure resilience and reliability. Despite the importance of these techniques, there lacks a comprehensive review of FA and FI methodologies in AI systems. This study fills this gap by presenting a detailed survey of existing FA and FI approaches across six layers of AI systems. We systematically analyze 160 papers and repositories to answer three research questions including (1) what are the prevalent failures in AI systems, (2) what types of faults can current FI tools simulate, (3) what gaps exist between the simulated faults and real-world failures. Our findings reveal a taxonomy of AI system failures, assess the capabilities of existing FI tools, and highlight discrepancies between real-world and simulated failures. Moreover, this survey contributes to the field by providing a framework for fault diagnosis, evaluating the state-of-the-art in FI, and identifying areas for improvement in FI techniques to enhance the resilience of AI systems.

cs.SE↗

arXiv2026

MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs

Large language models (LLMs) have been shown to memorize and reproduce content from their training data, raising significant privacy concerns, especially with web-scale datasets. Existing methods for detecting memorization are primarily sample-specific, relying on manually crafted or discretely optimized memory-inducing prompts generated on a per-sample basis, which become impractical for dataset-level detection due to the prohibitive computational cost of iterating through all samples. In real-world scenarios, data owners may need to verify whether a susceptible LLM has memorized their dataset, particularly if the LLM may have collected the data from the web without authorization. To address this, we introduce MemHunter, which trains a memory-inducing LLM and employs hypothesis testing to efficiently detect memorization at the dataset level, without requiring sample-specific memory inducing. Experiments on models like Pythia and Llama demonstrate that MemHunter can extract up to 40% more training data than existing methods under constrained time resources and reduce search time by up to 80% when integrated as a plug-in. Crucially, MemHunter is the first method capable of dataset-level memorization detection, providing a critical tool for assessing privacy risks in LLMs powered by large-scale datasets.

cs.CR↗

arXiv2026

SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks

Constructing large-scale datasets for the GitHub issue resolution task is crucial for both training and evaluating the software engineering capabilities of Large Language Models (LLMs). However, the existing GitHub issue resolution data construction pipeline is challenging and labor-intensive. We identify three key limitations in existing pipelines: (1) test patches collected often omit binary file changes; (2) the manual construction of evaluation environments is labor-intensive; and (3) the fail2pass validation phase requires manual inspection of test logs and writing custom parsing code to extract test status from logs. In this paper, we propose SWE-Factory, a fully automated issue resolution data construction pipeline, to resolve these limitations. First, our pipeline automatically recovers missing binary test files and ensures the correctness of test patches. Second, we introduce SWE-Builder, a LLM-based multi-agent system that automates evaluation environment construction. Third, we introduce a standardized, exit-code-based log parsing method to automatically extract test status, enabling a fully automated fail2pass validation. Experiments on 671 real-world GitHub issues across four programming languages show that our method can effectively construct valid evaluation environments for GitHub issues at a reasonable cost. For example, with GPT-4.1 mini, our SWE-Builder constructs 337 valid task instances out of 671 issues, at $0.047 per instance. Our ablation study further shows the effectiveness of different components of SWE-Builder. We also demonstrate through manual inspection that our exit-code-based fail2pass validation method is highly accurate, achieving an F1 score of 0.99. Additionally, we conduct an exploratory experiment to investigate whether we can use SWE-Factory to enhance models' software engineering ability.

cs.SE↗

arXiv2025

RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation

Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source repository. Many benchmarks have been proposed to evaluate the performance of such code translators. However, previous benchmarks mostly provide fine-grained samples, focusing at either code snippet, function, or file-level code translation. Such benchmarks do not accurately reflect real-world demands, where entire repositories often need to be translated, involving longer code length and more complex functionalities. To address this gap, we propose a new benchmark, named RepoTransBench, which is a real-world multilingual repository-level code translation benchmark featuring 1,897 real-world repository samples across 13 language pairs with automatically executable test suites. Besides, we introduce RepoTransAgent, a general agent framework to perform repository-level code translation. We evaluate both our benchmark's challenges and agent's effectiveness using several methods and backbone LLMs, revealing that repository-level translation remains challenging, where the best-performing method achieves only a 32.8% success rate. Furthermore, our analysis reveals that translation difficulty varies significantly by language pair direction, with dynamic-to-static language translation being much more challenging than the reverse direction (achieving below 10% vs. static-to-dynamic at 45-63%). Finally, we conduct a detailed error analysis and highlight current LLMs' deficiencies in repository-level code translation, which could provide a reference for further improvements. We provide the code and data at https://github.com/DeepSoftwareAnalytics/RepoTransBench.

cs.SE↗

arXiv2025

Alada: Alternating Adaptation of Momentum Method for Memory-Efficient Matrix Optimization

This work proposes Alada, an adaptive momentum method for stochastic optimization over large-scale matrices. Alada employs a rank-one factorization approach to estimate the second moment of gradients, where factors are updated alternatively to minimize the estimation error. Alada achieves sublinear memory overheads and can be readily extended to optimizing tensor-shaped variables.We also equip Alada with a first moment estimation rule, which enhances the algorithm's robustness without incurring additional memory overheads. The theoretical performance of Alada aligns with that of traditional methods such as Adam. Numerical studies conducted on several natural language processing tasks demonstrate the reduction in memory overheads and the robustness in training large models relative to Adam and its variants.

cs.LG↗

arXiv2025

SimpleDevQA: Benchmarking Large Language Models on Development Knowledge QA

The Development Knowledge Question Answering (Dev Knowledge QA) task aims to provide natural language answers to knowledge-seeking questions during software development. To investigate its importance and to what extent it has been explored, we analyze real user-LLM dialogues from WildChat and find that: (1) The Dev Knowledge QA task accounts for 39.6% of interactions(highest among all tasks), revealing broad knowledge needs beyond code generation (32.3%). (2) Only 27.5% of real Dev Knowledge QA dialogues focus on code understanding, leaving out development knowledge-seeking. (3) Only 17.1% of real-world Dev Knowledge QA dialogues can be used for constructing a benchmark. Existing benchmarks have two primary limitations for evaluating the Dev Knowledge QA capability of LLMs. First, existing benchmarks offer a limited development knowledge scope, mainly focusing on code understanding and neglecting broader knowledge during development. Second, some benchmarks are not built from real user queries. To bridge this gap, we design a three-phase pipeline that transforms real-world dialogue into simple development knowledge-seeking QA pairs. Through this pipeline, we introduce SimpleDevQA, a multilingual benchmark derived from real user dialogues. It contains 2,740 QA pairs in three languages (English, Chinese, and Russian), and focuses on questions with unique, short, and verifiable answers for accurate and simple evaluation. Experiments show that: Code LLMs generally outperform general LLMs of similar scale; Knowledge injection with the Retrieval-Augmented Generation (RAG) strategy can boost LLM accuracy by 11.3% on average; LLMs show systematic overconfidence in Dev Knowledge QA, and the answering accuracy of LLMs shows a positive correlation with their stated confidence; Generally, LLMs with stronger code generation performance also exhibit stronger performance in Dev Knowledge QA.

cs.SE↗

arXiv2025

An Empirical Study on Low-Code Programming using Traditional vs Large Language Model Support

Low-code programming (LCP) refers to programming using models at higher levels of abstraction, resulting in less manual and more efficient programming, and reduced learning effort for amateur developers. Many LCP tools have rapidly evolved and have benefited from the concepts of visual programming languages (VPLs) and programming by demonstration (PBD). With the huge increase in interest in using large language models (LLMs) in software engineering, LLM-based LCP has begun to become increasingly important. However, the technical principles and application scenarios of traditional approaches to LCP and LLM-based LCP are significantly different. Understanding these key differences and characteristics in the application of the two approaches to LCP by users is crucial for LCP providers in improving existing and developing new LCP tools and in better assisting users in choosing the appropriate LCP technology. We conducted an empirical study of both traditional LCP and LLM-based LCP. We analyzed developers' discussions on Stack Overflow (SO) over the past three years and then explored the similarities and differences between traditional LCP and LLM-based LCP features and developer feedback. Our findings reveal that while traditional LCP and LLM-based LCP share common primary usage scenarios, they significantly differ in scope, limitations, and usage throughout the software development lifecycle, particularly during the implementation phase. We also examine how LLMs impact and integrate with LCP, discussing the latest technological developments in LLM-based LCP, such as its integration with VPLs and the application of LLM Agents in software engineering.

cs.SE↗

arXiv2025

Metronome: Differentiated Delay Scheduling for Serverless Functions

Function-as-a-Service (FaaS) computing is an emerging cloud computing paradigm for its ease-of-management and elasticity. However, optimizing scheduling for serverless functions remains challenging due to their dynamic and event-driven nature. While data locality has been proven effective in traditional cluster computing systems through delay scheduling, its application in serverless platforms remains largely unexplored. In this paper, we systematically evaluate existing delay scheduling methods in serverless environments and identify three key observations: 1) delay scheduling benefits vary significantly based on function input characteristics; 2) serverless computing exhibits more complex locality patterns than cluster computing systems, encompassing both data locality and infrastructure locality; and 3) heterogeneous function execution times make rule-based delay thresholds ineffective. Based on these insights, we propose Metronome, a differentiated delay scheduling framework that employs predictive mechanisms to identify optimal locality-aware nodes for individual functions. Metronome leverages an online Random Forest Regression model to forecast function execution times across various nodes, enabling informed delay decisions while preventing SLA violations. Our implementation on OpenLambda shows that Metronome significantly outperforms baselines, achieving 64.88%-95.83% reduction in mean execution time for functions, while maintaining performance advantages under increased concurrency levels and ensuring SLA compliance.

cs.SE↗

arXiv2025

An Empirical Study of Agent Developer Practices in AI Agent Frameworks

The rise of large language models (LLMs) has sparked a surge of interest in agents, leading to the rapid growth of agent frameworks. Agent frameworks are software toolkits and libraries that provide standardized components, abstractions, and orchestration mechanisms to simplify agent development. Despite widespread use of agent frameworks, their practical applications and how they influence the agent development process remain underexplored. Different agent frameworks encounter similar problems during use, indicating that these recurring issues deserve greater attention and call for further improvements in agent framework design. Meanwhile, as the number of agent frameworks continues to grow and evolve, more than 80% of developers report difficulties in identifying the frameworks that best meet their specific development requirements. In this paper, we conduct the first empirical study of LLM-based agent frameworks, exploring real-world experiences of developers in building AI agents. To compare how well the agent frameworks meet developer needs, we further collect developer discussions for the ten previously identified agent frameworks, resulting in a total of 11,910 discussions. Finally, by analyzing these discussions, we compare the frameworks across five dimensions: development efficiency, functional abstraction, learning cost, performance optimization, and maintainability, which refers to how easily developers can update and extend both the framework itself and the agents built upon it over time. Our comparative analysis reveals significant differences among frameworks in how they meet the needs of agent developers. Overall, we provide a set of findings and implications for the LLM-driven AI agent framework ecosystem and offer insights for the design of future LLM-based agent frameworks and agent developers.

cs.SE↗

arXiv2025

An Empirical Study on the Security Vulnerabilities of GPTs

Equipped with various tools and knowledge, GPTs, one kind of customized AI agents based on OpenAI's large language models, have illustrated great potential in many fields, such as writing, research, and programming. Today, the number of GPTs has reached three millions, with the range of specific expert domains becoming increasingly diverse. However, given the consistent framework shared among these LLM agent applications, systemic security vulnerabilities may exist and remain underexplored. To fill this gap, we present an empirical study on the security vulnerabilities of GPTs. Building upon prior research on LLM security, we first adopt a platform-user perspective to conduct a comprehensive attack surface analysis across different system components. Then, we design a systematic and multidimensional attack suite with the explicit objectives of information leakage and tool misuse based on the attack surface analysis, thereby concretely demonstrating the security vulnerabilities that various components of GPT-based systems face. Finally, we accordingly propose defense mechanisms to address the aforementioned security vulnerabilities. By increasing the awareness of these vulnerabilities and offering critical insights into their implications, this study seeks to facilitate the secure and responsible application of GPTs while contributing to developing robust defense mechanisms that protect users and systems against malicious attacks.

cs.CR↗