arXiv subjects

David Lo

Publications and source records attributed to David Lo.

At least 109 records · Page 6Linked to original sources

arXiv2026

What You Trust Is Insecure: Demystifying How Developers (Mis)Use Trusted Execution Environments in Practice

Trusted Execution Environments (TEEs), such as Intel SGX and ARM TrustZone, provide isolated regions of CPU and memory for secure computation and are increasingly used to protect sensitive data and code across diverse application domains. However, little is known about how developers actually use TEEs in practice. This paper presents the first large-scale empirical study of real-world TEE applications. We collected and analyzed 241 open-source projects from GitHub that utilize the two most widely-adopted TEEs, Intel SGX and ARM TrustZone. By combining manual inspection with customized static analysis scripts, we examined their adoption contexts, usage patterns, and development practices across three phases. First, we categorized the projects into 8 application domains and identified trends in TEE adoption over time. We found that the dominant use case is IoT device security (30%), which contrasts sharply with prior academic focus on blockchain and cryptographic systems (7%), while AI model protection (12%) is rapidly emerging as a growing domain. Second, we analyzed how TEEs are integrated into software and observed that 32.4% of the projects reimplement cryptographic functionalities instead of using official SDK APIs, suggesting that current SDKs may have limited usability and portability to meet developers' practical needs. Third, we examined security practices through manual inspection and found that 25.3% (61 of 241) of the projects exhibit insecure coding behaviors when using TEEs, such as hardcoded secrets and missing input validation, which undermine their intended security guarantees. Our findings have important implications for improving the usability of TEE SDKs and supporting developers in trusted software development.

cs.SE↗

arXiv2026

Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?

Automated vulnerability detection research has made substantial progress, yet its real-world impact remains limited. Prior work found that current vulnerability datasets suffer from issues including label inaccuracy rates of 20%-71%, extensive duplication, and poor coverage of critical Common Weakness Enumeration (CWE). These issues create a significant generalization gap where models achieve misleading In-Distribution (ID) accuracies (testing on splits from the same dataset) by exploiting spurious correlations rather than learning true vulnerability patterns. To address these limitations, we present a three-part solution. First, we introduce BenchVul, which is a manually curated and balanced test dataset covering the MITRE Top 25 Most Dangerous CWEs, to enable fair model evaluation. Second, we construct a high-quality training dataset, TitanVul, comprising 38,548 functions by aggregating seven public sources and applying deduplication and validation using a novel multi-agent LLM pipeline. Third, we propose a Realistic Vulnerability Generation (RVG) pipeline, which synthesizes context-aware vulnerability examples for underrepresented but critical CWE types through simulated development workflows. Our evaluation reveals that In-Distribution (ID) performance does not reliably predict Out-of-Distribution (OOD) performance on BenchVul. For example, a model trained on BigVul achieves the highest 0.703 ID accuracy but fails on BenchVul's real-world samples (0.493 OOD accuracy). Conversely, a model trained on our TitanVul achieves the highest OOD performance on both the real-world (0.881) and synthesized (0.785) portions of BenchVul, improving upon the next-best performing dataset by 5.3% and 11.8% respectively, despite a modest ID score (0.590). Augmenting TitanVul with our RVG further boosts this leading OOD performance, improving accuracy on real-world data by 5.8% (to 0.932).

cs.CR↗

arXiv2026

PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing

Penetration testing is essential for identifying vulnerabilities in web applications before real adversaries can exploit them. Recent work has explored automating this process with Large Language Model (LLM)-powered agents, but existing approaches either rely on a single generic agent that struggles in complex scenarios or narrowly specialized agents that cannot adapt to diverse vulnerability types. We therefore introduce PenForge, a framework that dynamically constructs expert agents during testing rather than relying on those prepared beforehand. By integrating automated reconnaissance of potential attack surfaces with agents instantiated on the fly for context-aware exploitation, PenForge achieves a 30.0% exploit success rate (12/40) on CVE-Bench in the particularly challenging zero-day setting, which is a 3 times improvement over the state-of-the-art. Our analysis also identifies three opportunities for future work: (1) supplying richer tool-usage knowledge to improve exploitation effectiveness; (2) extending benchmarks to include more vulnerabilities and attack types; and (3) fostering developer trust by incorporating explainable mechanisms and human review. As an emerging result with substantial potential impact, PenForge embodies the early-stage yet paradigm-shifting idea of on-the-fly agent construction, marking its promise as a step toward scalable and effective LLM-driven penetration testing.

cs.SE↗

arXiv2025

Why Is My Transaction Risky? Understanding Smart Contract Semantics and Interactions in the NFT Ecosystem

The NFT ecosystem represents an interconnected, decentralized environment that encompasses the creation, distribution, and trading of Non-Fungible Tokens (NFTs), where key actors, such as marketplaces, sellers, and buyers, utilize smart contracts to facilitate secure, transparent, and trustless transactions. Scam tokens are deliberately created to mislead users and facilitate financial exploitation, posing significant risks in the NFT ecosystem. Prior work has explored the NFT ecosystem from various perspectives, including security challenges, actor behaviors, and risks from scams and wash trading, leaving a gap in understanding the semantics and interactions of smart contracts during transactions, and how the risks associated with scam tokens manifest in relation to the semantics and interactions of contracts. To bridge this gap, we conducted a large-scale empirical study on smart contract semantics and interactions in the NFT ecosystem, using a curated dataset of nearly 100 million transactions across 20 million blocks on Ethereum. We observe a limited semantic diversity among smart contracts in the NFT ecosystem, dominated by proxy, token, and DeFi contracts. Marketplace and proxy registry contracts are the most frequently involved in smart contract interactions during transactions, engaging with a broad spectrum of contracts in the ecosystem. Token contracts exhibit bytecode-level diversity, whereas scam tokens exhibit bytecode convergence. Certain interaction patterns between smart contracts are common to both risky and non-risky transactions, while others are predominantly associated with risky transactions. Based on our findings, we provide recommendations to mitigate risks in the blockchain ecosystem, and outline future research directions.

cs.SE↗

arXiv2025

Identifying and Mitigating API Misuse in Large Language Models

API misuse in code generated by large language models (LLMs) presents a serious and growing challenge in software development, as although LLMs demonstrate impressive code generation capabilities, their interactions with complex library APIs are often error-prone and can lead to software failures and vulnerabilities. In this paper, we conduct a large-scale study of API misuse patterns in LLM-generated code by analyzing both method selection and parameter usage across Python and Java, using three representative LLMs: StarCoder-7B, Qwen2.5-Coder-7B, and GitHub Copilot. Based on extensive manual annotation of 3,209 method-level and 3,492 parameter-level misuses, we identify and categorize four recurring misuse types by building on and refining prior API misuse taxonomies. Our evaluation of the three LLMs reveals persistent challenges in API usage, particularly hallucination and intent misalignment. To address these issues, we propose Dr.Fix, an LLM-based automatic repair approach guided by our taxonomy, which improves repair accuracy compared to baseline prompting and existing repair methods, achieving gains of up to 38.4 BLEU and 40% exact match on benchmark datasets. This work offers important insights into the current limitations of LLMs in API usage and points to directions for improving automated misuse repair in code generation systems.

cs.SE↗

arXiv2025

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.

cs.SE↗

arXiv2025

Aligning Academia with Industry: An Empirical Study of Industrial Needs and Academic Capabilities in AI-Driven Software Engineering

The rapid advancement of large language models (LLMs) is fundamentally reshaping software engineering (SE), driving a paradigm shift in both academic research and industrial practice. While top-tier SE venues continue to show sustained or emerging focus on areas like automated testing and program repair, with researchers worldwide reporting continuous performance gains, the alignment of these academic advances with real industrial needs remains unclear. To bridge this gap, we first conduct a systematic analysis of 1,367 papers published in FSE, ASE, and ICSE between 2022 and 2025, identifying key research topics, commonly used benchmarks, industrial relevance, and open-source availability. We then carry out an empirical survey across 17 organizations, collecting 282 responses on six prominent topics, i.e., program analysis, automated testing, code generation/completion, issue resolution, pre-trained code models, and dependency management, through structured questionnaires. By contrasting academic capabilities with industrial feedback, we derive seven critical implications, highlighting under-addressed challenges in software requirements and architecture, the reliability and explainability of intelligent SE approaches, input assumptions in academic research, practical evaluation tensions, and ethical considerations. This study aims to refocus academic attention on these important yet under-explored problems and to guide future SE research toward greater industrial impact.

cs.SE↗

arXiv2025

CREME: Robustness Enhancement of Code LLMs via Layer-Aware Model Editing

Large language models (LLMs) have demonstrated impressive capabilities in code generation, where the natural language prompt plays a crucial role in conveying user intent to the model. However, prior studies have shown that LLMs are highly sensitive to prompt perturbations. Minor modifications in wording, syntax, or formatting can significantly reduce the functional correctness of generated code. As perturbations frequently occur in real-world scenarios, improving the robustness of LLMs to prompt perturbations is essential for ensuring reliable performance in practical code generation. In this paper, we introduce CREME (Code Robustness Enhancement via Model Editing), a novel approach that enhances LLM robustness through targeted parameter updates. CREME first identifies robustness-sensitive layers by comparing hidden states between an original prompt and its perturbed variant. Then, it performs lightweight parameter editing at the identified layer to reduce performance degradation. We evaluate CREME on two widely used code generation benchmarks (HumanEval and MBPP) along with their perturbed counterparts. Experimental results show that CREME improves Pass@1 accuracy by 63% on perturbed prompts while maintaining stable performance on clean inputs, with accuracy deviations within 1%. Further analysis reveals that robustness-sensitive layers are primarily concentrated in the middle and deeper layers of the network, and their locations vary across different model architectures. These insights provide a valuable foundation for developing future robustness-oriented editing strategies.

cs.SE↗

arXiv2025

Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand

Large language models (LLMs) have shown exceptional performance in code generation and understanding tasks, yet their high computational costs hinder broader adoption. One important factor is the inherent verbosity of programming languages, such as unnecessary formatting elements and lengthy boilerplate code. This leads to inflated token counts in both input and generated outputs, which increases inference costs and slows down the generation process. Prior work improves this through simplifying programming language grammar, reducing token usage across both code understanding and generation tasks. However, it is confined to syntactic transformations, leaving significant opportunities for token reduction unrealized at the semantic level. In this work, we propose Token Sugar, a concept that replaces frequent and verbose code patterns with reversible, token-efficient shorthand in the source code. To realize this concept in practice, we designed a systematic solution that mines high-frequency, token-heavy patterns from a code corpus, maps each to a unique shorthand, and integrates them into LLM pretraining via code transformation. With this solution, we obtain 799 (code pattern, shorthand) pairs, which can reduce up to 15.1% token count in the source code and is complementary to existing syntax-focused methods. We further trained three widely used LLMs on Token Sugar-augmented data. Experimental results show that these models not only achieve significant token savings (up to 11.2% reduction) during generation but also maintain near-identical Pass@1 scores compared to baselines trained on unprocessed code.

cs.SE↗

arXiv2025

Cataloguing Hugging Face Models to Software Engineering Activities: Automation and Findings

Context: Open-source Pre-Trained Models (PTMs) provide extensive resources for various Machine Learning (ML) tasks, yet these resources lack a classification tailored to Software Engineering (SE) needs to support the reliable identification and reuse of models for SE. Objective: To address this gap, we derive a taxonomy encompassing 147 SE tasks and apply an SE-oriented classification to PTMs in a popular open-source ML repository, Hugging Face (HF). Method: Our repository mining study followed a five-phase pipeline: (i) identification SE tasks from the literature; (ii) collection of PTM data from the HF API, including model card descriptions and metadata, and the abstracts of the associated arXiv papers; (iii) text processing to ensure consistency; (iv) a two-phase validation of SE relevance, involving humans and LLM assistance, supported by five pilot studies with human annotators and a generalization test; (v) and data analysis. This process yielded a curated catalogue of 2,205 SE PTMs. Results: We find that most SE PTMs target code generation and coding, emphasizing implementation over early or late development stages. In terms of ML tasks, text generation dominates within SE PTMs. Notably, the number of SE PTMs has increased markedly since 2023 Q2, while evaluation remains limited: only 9.6% report benchmark results, mostly scoring below 50%. Conclusions: Our catalogue reveals documentation and transparency gaps, highlights imbalances across SDLC phases, and provides a foundation for automated SE scenarios, such as the sampling and selection of suitable PTMs.

cs.SE↗

arXiv2025

Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents

Detecting vulnerabilities in source code remains a critical yet challenging task, especially when benign and vulnerable functions share significant similarities. In this work, we introduce VulTrial, a courtroom-inspired multi-agent framework designed to identify vulnerable code and to provide explanations. It employs four role-specific agents, which are security researcher, code author, moderator, and review board. Using GPT-4o as the base LLM, VulTrial almost doubles the efficacy of prior best-performing baselines. Additionally, we show that role-specific instruction tuning with small quantities of data significantly further boosts VulTrial's efficacy. Our extensive experiments demonstrate the efficacy of VulTrial across different LLMs, including an open-source, in-house-deployable model (LLaMA-3.1-8B), as well as the high quality of its generated explanations and its ability to uncover multiple confirmed zero-day vulnerabilities in the wild.

cs.SE↗

arXiv2025

How do Machine Learning Models Change?

The proliferation of Machine Learning (ML) models and their open-source implementations has transformed Artificial Intelligence research and applications. Platforms like Hugging Face (HF) enable this evolving ecosystem, yet a large-scale longitudinal study of how these models change is lacking. This study addresses this gap by analyzing over 680,000 commits from 100,000 models and 2,251 releases from 202 of these models on HF using repository mining and longitudinal methods. We apply an extended ML change taxonomy to classify commits and use Bayesian networks to model temporal patterns in commit and release activities. Our findings show that commit activities align with established data science methodologies, such as the Cross-Industry Standard Process for Data Mining (CRISP-DM), emphasizing iterative refinement. Release patterns tend to consolidate significant updates, particularly in model outputs, sharing, and documentation, distinguishing them from granular commits. Furthermore, projects with higher popularity exhibit distinct evolutionary paths, often starting from a more mature baseline with fewer foundational commits in their public history. In contrast, those with intensive collaboration show unique documentation and technical evolution patterns. These insights enhance the understanding of model changes on community platforms and provide valuable guidance for best practices in model maintenance.

cs.SE↗

arXiv2025

Assessing and Advancing Benchmarks for Evaluating Large Language Models in Software Engineering Tasks

Large language models (LLMs) are gaining increasing popularity in software engineering (SE) due to their unprecedented performance across various applications. These models are increasingly being utilized for a range of SE tasks, including requirements engineering and design, code analysis and generation, software maintenance, and quality assurance. As LLMs become more integral to SE, evaluating their effectiveness is crucial for understanding their potential in this field. In recent years, substantial efforts have been made to assess LLM performance in various SE tasks, resulting in the creation of several benchmarks tailored to this purpose. This paper offers a thorough review of 291 benchmarks, addressing three main aspects: what benchmarks are available, how benchmarks are constructed, and the future outlook for these benchmarks. We begin by examining SE tasks such as requirements engineering and design, coding assistant, software testing, AIOPs, software maintenance, and quality management. We then analyze the benchmarks and their development processes, highlighting the limitations of existing benchmarks. Additionally, we discuss the successes and failures of LLMs in different software tasks and explore future opportunities and challenges for SE-related benchmarks. We aim to provide a comprehensive overview of benchmark research in SE and offer insights to support the creation of more effective evaluation tools.

cs.SE↗

arXiv2025

A Systematic Literature Review of Code Hallucinations in LLMs: Characterization, Mitigation Methods, Challenges, and Future Directions for Reliable AI

Model hallucination is one of the most critical challenges faced by Large Language Models (LLMs), especially in high-stakes code intelligence tasks. As LLMs become increasingly integrated into software engineering tasks, understanding and mitigating hallucination in code becomes essential. In this survey, we provide a systematic review of hallucination phenomena in code-oriented LLMs from four key perspectives. First, we begin by surveying 60 papers to define hallucination in the context of code and summarize its primary causes, such as data noise, exposure bias, and insufficient semantic grounding, while also tracing recent trends in literature across natural language processing (NLP) and software engineering communities. Second, we review model hallucination surveys in a broader span and summarize representative hallucination mitigation strategies, such as knowledge-enhanced generation, constrained decoding, and post-editing. Third, we review approaches targeted for code intelligence and highlight code-specific challenges that aggravate hallucination, including syntax sensitivity, strict type systems, and dependence on external libraries. Meanwhile, we analyze how emerging code intelligence tasks, e.g., program analysis, symbolic execution, and unit testing, are utilized to detect and mitigate hallucinations. Fourth, we summarize current evaluation benchmarks, ranging from static metrics to dynamic checks, e.g., compilation and execution correctness, and emphasize the need for hallucination-oriented benchmarks.

cs.SE↗

arXiv2025

LLM-as-a-Judge for Software Engineering: Literature Review, Vision, and the Road Ahead

The rapid integration of Large Language Models (LLMs) into software engineering (SE) has revolutionized tasks like code generation, producing a massive volume of software artifacts. This surge has exposed a critical bottleneck: the lack of scalable, reliable methods to evaluate these outputs. Human evaluation is costly and time-consuming, while traditional automated metrics like BLEU fail to capture nuanced quality aspects. In response, the LLM-as-a-Judge paradigm - using LLMs for automated evaluation - has emerged. This approach leverages the advanced reasoning of LLMs, offering a path toward human-like nuance at automated scale. However, LLM-as-a-Judge research in SE is still in its early stages. This forward-looking SE 2030 paper aims to steer the community toward advancing LLM-as-a-Judge for evaluating LLM-generated software artifacts. We provide a literature review of existing SE studies, analyze their limitations, identify key research gaps, and outline a detailed roadmap. We envision these frameworks as reliable, robust, and scalable human surrogates capable of consistent, multi-faceted artifact evaluation by 2030. Our work aims to foster research and adoption of LLM-as-a-Judge frameworks, ultimately improving the scalability of software artifact evaluation.

cs.SE↗

arXiv2025

Synthesizing Efficient and Permissive Programmatic Runtime Shields for Neural Policies

With the increasing use of neural policies in control systems, ensuring their safety and reliability has become a critical software engineering task. One prevalent approach to ensuring the safety of neural policies is to deploy programmatic runtime shields alongside them to correct their unsafe commands. However, the programmatic runtime shields synthesized by existing methods are either computationally expensive or insufficiently permissive, resulting in high overhead and unnecessary interventions on the system. To address these challenges, we propose Aegis, a novel framework that synthesizes lightweight and permissive programmatic runtime shields for neural policies. Aegis achieves this by formulating the seeking of a runtime shield as a sketch-based program synthesis problem and proposing a novel method that leverages counterexample-guided inductive synthesis and Bayesian optimization to solve it. To evaluate Aegis and its synthesized shields, we use eight representative control systems and compare Aegis with the current state-of-the-art. Our results show that the programmatic runtime shields synthesized by Aegis can correct all unsafe commands from neural policies, ensuring that the systems do not violate any desired safety properties at all times. Compared to the current state-of-the-art, Aegis's shields exhibit a 2.2$\times$ reduction in time overhead and a 3.9$\times$ reduction in memory usage, suggesting that they are much more lightweight. Moreover, Aegis's shields incur an average of 1.5$\times$ fewer interventions than other shields, showing better permissiveness.

cs.SE↗

arXiv2025

Trace: Securing Smart Contract Repository Against Access Control Vulnerability

Smart contract vulnerabilities, particularly improper Access Control that allows unauthorized execution of restricted functions, have caused billions of dollars in losses. GitHub hosts numerous smart contract repositories containing source code, documentation, and configuration files-these serve as intermediate development artifacts that must be compiled and packaged before deployment. Third-party developers often reference, reuse, or fork code from these repositories during custom development. However, if the referenced code contains vulnerabilities, it can introduce significant security risks. Existing tools for detecting smart contract vulnerabilities are limited in their ability to handle complex repositories, as they typically require the target contract to be compilable to generate an abstract representation for further analysis. This paper presents TRACE, a tool designed to secure non-compilable smart contract repositories against access control vulnerabilities. TRACE employs LLMs to locate sensitive functions involving critical operations (e.g., transfer) within the contract and subsequently completes function snippets into a fully compilable contract. TRACE constructs a function call graph from the abstract syntax tree (AST) of the completed contract. It uses the control flow graph (CFG) of each function as node information. The nodes of the sensitive functions are then analyzed to detect Access Control vulnerabilities. Experimental results demonstrate that TRACE outperforms state-of-the-art tools on an open-sourced CVE dataset, detecting 14 out of 15 CVEs. In addition, it achieves 89.2% precision on 5,000 recent on-chain contracts, far exceeding the best existing tool at 76.9%. On 83 real-world repositories, TRACE achieves 87.0% precision, significantly surpassing DeepSeek-R1's 14.3%.

cs.SE↗

arXiv2025

Beyond Surface Similarity: Evaluating LLM-Based Test Refactorings with Structural and Semantic Awareness

Large Language Models (LLMs) are increasingly used to refactor unit tests, improving readability and structure while preserving behavior. Evaluating such refactorings, however, remains difficult: metrics like CodeBLEU penalize beneficial renamings and edits, while semantic similarities overlook readability and modularity. We propose CTSES, a first step toward human-aligned evaluation of refactored tests. CTSES combines CodeBLEU, METEOR, and ROUGE-L into a composite score that balances semantics, lexical clarity, and structural alignment. Evaluated on 5,000+ refactorings from Defects4J and SF110 (GPT-4o and Mistral-Large), CTSES reduces false negatives and provides more interpretable signals than individual metrics. Our emerging results illustrate that CTSES offers a proof-of-concept for composite approaches, showing their promise in bridging automated metrics and developer judgments.

cs.SE↗