arXiv subjects

Jiamou Sun

Publications and source records attributed to Jiamou Sun.

16 recordsLinked to original sources

arXiv2026

Favia: Forensic Agent for Vulnerability-fix Identification and Analysis

Identifying vulnerability-fixing commits corresponding to disclosed CVEs is essential for secure software maintenance but remains challenging at scale, as large repositories contain millions of commits of which only a small fraction address security issues. Existing automated approaches, including traditional machine learning techniques and recent large language model (LLM)-based methods, often suffer from poor precision-recall trade-offs. Frequently evaluated on randomly sampled commits, we uncover that they are substantially underestimating real-world difficulty, where candidate commits are already security-relevant and highly similar. We propose Favia, a forensic, agent-based framework for vulnerability-fix identification that combines scalable candidate ranking with deep and iterative semantic reasoning. Favia first employs an efficient ranking stage to narrow the search space of commits. Each commit is then rigorously evaluated using a ReAct-based LLM agent. By providing the agent with a pre-commit repository as environment, along with specialized tools, the agent tries to localize vulnerable components, navigates the codebase, and establishes causal alignment between code changes and vulnerability root causes. This evidence-driven process enables robust identification of indirect, multi-file, and non-trivial fixes that elude single-pass or similarity-based methods. We evaluate Favia on CVEVC, a large-scale dataset we made that comprises over 8 million commits from 3,708 real-world repositories, and show that it consistently outperforms state-of-the-art traditional and LLM-based baselines under realistic candidate selection, achieving the strongest precision-recall trade-offs and highest F1-scores.

cs.SE↗

arXiv2025

Domain-constrained Synthesis of Inconsistent Key Aspects in Textual Vulnerability Descriptions

Textual Vulnerability Descriptions (TVDs) are crucial for security analysts to understand and address software vulnerabilities. However, the key aspect inconsistencies in TVDs from different repositories pose challenges for achieving a comprehensive understanding of vulnerabilities. Existing approaches aim to mitigate inconsistencies by aligning TVDs with external knowledge bases, but they often discard valuable information and fail to synthesize comprehensive representations. In this paper, we propose a domain-constrained LLM-based synthesis framework for unifying key aspects of TVDs. Our framework consists of three stages: 1) Extraction, guided by rule-based templates to ensure all critical details are captured; 2) Self-evaluation, using domain-specific anchor words to assess semantic variability across sources; and 3) Fusion, leveraging information entropy to reconcile inconsistencies and prioritize relevant details. This framework improves synthesis performance, increasing the F1 score for key aspect augmentation from 0.82 to 0.87, while enhancing comprehension and efficiency by over 30\%. We further develop Digest Labels, a practical tool for visualizing TVDs, which human evaluations show significantly boosts usability.

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

HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities

Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While language model agents show promise in cybersecurity, modern web applications demand visual understanding, dynamic content handling, and multi-step interactions that only computer-use agents (CUAs) can perform. Yet, their ability to discover and exploit vulnerabilities through graphical interfaces remains largely unexplored. We present HackWorld, the first framework for systematically evaluating CUAs' capabilities to exploit web application vulnerabilities via visual interaction. Unlike sanitized benchmarks, HackWorld includes 36 real-world applications across 11 frameworks and 7 languages, featuring realistic flaws such as injection vulnerabilities, authentication bypasses, and unsafe input handling. Using a Capture-the-Flag (CTF) setup, it tests CUAs' capacity to identify and exploit these weaknesses while navigating complex web interfaces. Evaluation of state-of-the-art CUAs reveals concerning trends: exploitation rates below 12% and low cybersecurity awareness. CUAs often fail at multi-step attack planning and misuse security tools. These results expose the current limitations of CUAs in web security contexts and highlight opportunities for developing more security-aware agents capable of effective vulnerability detection and exploitation.

cs.CR↗

arXiv2025

Bridging Solidity Evolution Gaps: An LLM-Enhanced Approach for Smart Contract Compilation Error Resolution

Solidity, the dominant smart contract language for Ethereum, has rapidly evolved with frequent version updates to enhance security, functionality, and developer experience. However, these continual changes introduce significant challenges, particularly in compilation errors, code migration, and maintenance. Therefore, we conduct an empirical study to investigate the challenges in the Solidity version evolution and reveal that 81.68% of examined contracts encounter errors when compiled across different versions, with 86.92% of compilation errors. To mitigate these challenges, we conducted a systematic evaluation of large language models (LLMs) for resolving Solidity compilation errors during version migrations. Our empirical analysis across both open-source (LLaMA3, DeepSeek) and closed-source (GPT-4o, GPT-3.5-turbo) LLMs reveals that although these models exhibit error repair capabilities, their effectiveness diminishes significantly for semantic-level issues and shows strong dependency on prompt engineering strategies. This underscores the critical need for domain-specific adaptation in developing reliable LLM-based repair systems for smart contracts. Building upon these insights, we introduce SMCFIXER, a novel framework that systematically integrates expert knowledge retrieval with LLM-based repair mechanisms for Solidity compilation error resolution. The architecture comprises three core phases: (1) context-aware code slicing that extracts relevant error information; (2) expert knowledge retrieval from official documentation; and (3) iterative patch generation for Solidity migration. Experimental validation across Solidity version migrations demonstrates our approach's statistically significant 24.24% improvement over baseline GPT-4o on real-world datasets, achieving near-perfect 96.97% accuracy.

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

From Code to Courtroom: LLMs as the New Software Judges

Recently, Large Language Models (LLMs) have been increasingly used to automate SE tasks such as code generation and summarization. However, evaluating the quality of LLM-generated software artifacts remains challenging. Human evaluation, while effective, is very costly and time-consuming. Traditional automated metrics like BLEU rely on high-quality references and struggle to capture nuanced aspects of software quality, such as readability and usefulness. In response, the LLM-as-a-Judge paradigm, which employs LLMs for automated evaluation, has emerged. Given that LLMs are typically trained to align with human judgment and possess strong coding abilities and reasoning skills, they hold promise as cost-effective and scalable surrogates for human evaluators. Nevertheless, LLM-as-a-Judge research in the SE community is still in its early stages, with many breakthroughs needed. This forward-looking SE 2030 paper aims to steer the research community toward advancing LLM-as-a-Judge for evaluating LLMgenerated software artifacts, while also sharing potential research paths to achieve this goal. We provide a literature review of existing SE studies on LLM-as-a-Judge and envision these frameworks as reliable, robust, and scalable human surrogates capable of evaluating software artifacts with consistent, multi-faceted assessments by 2030 and beyond. To validate this vision, we analyze the limitations of current studies, identify key research gaps, and outline a detailed roadmap to guide future developments of LLM-as-a-Judge in software engineering. While not intended to be a definitive guide, our work aims to foster further research and adoption of LLM-as-a-Judge frameworks within the SE community, ultimately improving the effectiveness and scalability of software artifact evaluation methods.

cs.SE↗

arXiv2025

50 Shades of Deceptive Patterns: A Unified Taxonomy, Multimodal Detection, and Security Implications

Deceptive patterns (DPs) are user interface designs deliberately crafted to manipulate users into unintended decisions, often by exploiting cognitive biases for the benefit of companies or services. While numerous studies have explored ways to identify these deceptive patterns, many existing solutions require significant human intervention and struggle to keep pace with the evolving nature of deceptive designs. To address these challenges, we expanded the deceptive pattern taxonomy from security and privacy perspectives, refining its categories and scope. We created a comprehensive dataset of deceptive patterns by integrating existing small-scale datasets with new samples, resulting in 6,725 images and 10,421 DP instances from mobile apps and websites. We then developed DPGuard, a novel automatic tool leveraging commercial multimodal large language models (MLLMs) for deceptive pattern detection. Experimental results show that DPGuard outperforms state-of-the-art methods. Finally, we conducted an extensive empirical evaluation on 2,000 popular mobile apps and websites, revealing that 23.61% of mobile screenshots and 47.27% of website screenshots feature at least one deceptive pattern instance. Through four unexplored case studies that inform security implications, we highlight the critical importance of the unified taxonomy in addressing the growing challenges of Internet deception.

cs.CR↗

arXiv2024

From Exploration to Revelation: Detecting Dark Patterns in Mobile Apps

Mobile apps are essential in daily life but frequently employ deceptive patterns, such as visual emphasis or linguistic nudging, to manipulate user behavior. Existing research largely relies on manual detection, which is time-consuming and cannot keep pace with rapidly evolving apps. Although recent work has explored automated approaches, these methods are limited to intra-page patterns, depend on manual app exploration, and lack flexibility. To address these limitations, we present AppRay, a system that integrates task-oriented app exploration with automated deceptive pattern detection to reduce manual effort, expand detection coverage, and improve performance. AppRay operates in two stages. First, it combines large language model-guided task-oriented exploration with random exploration to capture diverse user interface (UI) states. Second, it detects both intra-page and inter-page deceptive patterns using a contrastive learning-based multi-label classifier augmented with a rule-based refiner for context-aware detection. We contribute two datasets, AppRay-Tainted-UIs and AppRay-Benign-UIs, comprising 2,185 deceptive pattern instances, including 149 intra-page cases, spanning 16 types across 876 deceptive and 871 benign UIs, while preserving UI relationships. Experimental results show that AppRay achieves macro/micro averaged precision of 0.92/0.85, recall of 0.86/0.88, and F1 scores of 0.89/0.85, yielding 27.14% to 1200% improvements over prior methods and enabling effective detection of previously unexplored deceptive patterns.

cs.SE↗

arXiv2024

Do Chase Your Tail! Missing Key Aspects Augmentation in Textual Vulnerability Descriptions of Long-tail Software through Feature Inference

Augmenting missing key aspects in Textual Vulnerability Descriptions (TVDs) is crucial for effective vulnerability analysis. For instance, in TVDs, key aspects include Attack Vector, Vulnerability Type, among others. These key aspects help security engineers understand and address the vulnerability in a timely manner. For software with a large user base (non-long-tail software), augmenting these missing key aspects has significantly advanced vulnerability analysis and software security research. However, software instances with a limited user base (long-tail software) often get overlooked due to inconsistency software names, TVD limited avaliability, and domain-specific jargon, which complicates vulnerability analysis and software repairs. In this paper, we introduce a novel software feature inference framework designed to augment the missing key aspects of TVDs for long-tail software. Firstly, we tackle the issue of non-standard software names found in community-maintained vulnerability databases by cross-referencing government databases with Common Vulnerabilities and Exposures (CVEs). Next, we employ Large Language Models (LLMs) to generate the missing key aspects. However, the limited availability of historical TVDs restricts the variety of examples. To overcome this limitation, we utilize the Common Weakness Enumeration (CWE) to classify all TVDs and select cluster centers as representative examples. To ensure accuracy, we present Natural Language Inference (NLI) models specifically designed for long-tail software. These models identify and eliminate incorrect responses. Additionally, we use a wiki repository to provide explanations for proprietary terms.

cs.SE↗

arXiv2024

The Invisible Game on the Internet: A Case Study of Decoding Deceptive Patterns

Deceptive patterns are design practices embedded in digital platforms to manipulate users, representing a widespread and long-standing issue in the web and mobile software development industry. Legislative actions highlight the urgency of globally regulating deceptive patterns. However, despite advancements in detection tools, a significant gap exists in assessing deceptive pattern risks. In this study, we introduce a comprehensive approach involving the interactions between the Adversary, Watchdog (e.g., detection tools), and Challengers (e.g., users) to formalize and decode deceptive pattern threats. Based on this, we propose a quantitative risk assessment system. Representative cases are analyzed to showcase the practicability of the proposed risk scoring system, emphasizing the importance of involving human factors in deceptive pattern risk assessment.

cs.CR↗

arXiv2023

Pop Quiz! Do Pre-trained Code Models Possess Knowledge of Correct API Names?

Recent breakthroughs in pre-trained code models, such as CodeBERT and Codex, have shown their superior performance in various downstream tasks. The correctness and unambiguity of API usage among these code models are crucial for achieving desirable program functionalities, requiring them to learn various API fully qualified names structurally and semantically. Recent studies reveal that even state-of-the-art pre-trained code models struggle with suggesting the correct APIs during code generation. However, the reasons for such poor API usage performance are barely investigated. To address this challenge, we propose using knowledge probing as a means of interpreting code models, which uses cloze-style tests to measure the knowledge stored in models. Our comprehensive study examines a code model's capability of understanding API fully qualified names from two different perspectives: API call and API import. Specifically, we reveal that current code models struggle with understanding API names, with pre-training strategies significantly affecting the quality of API name learning. We demonstrate that natural language context can assist code models in locating Python API names and generalize Python API name knowledge to unseen data. Our findings provide insights into the limitations and capabilities of current pre-trained code models, and suggest that incorporating API structure into the pre-training process can improve automated API usage and code representations. This work provides significance for advancing code intelligence practices and direction for future studies. All experiment results, data and source code used in this work are available at \url{https://doi.org/10.5281/zenodo.7902072}.

cs.SE↗

arXiv2023

Unveiling the Tricks: Automated Detection of Dark Patterns in Mobile Applications

Mobile apps bring us many conveniences, such as online shopping and communication, but some use malicious designs called dark patterns to trick users into doing things that are not in their best interest. Many works have been done to summarize the taxonomy of these patterns and some have tried to mitigate the problems through various techniques. However, these techniques are either time-consuming, not generalisable or limited to specific patterns. To address these issues, we propose UIGuard, a knowledge-driven system that utilizes computer vision and natural language pattern matching to automatically detect a wide range of dark patterns in mobile UIs. Our system relieves the need for manually creating rules for each new UI/app and covers more types with superior performance. In detail, we integrated existing taxonomies into a consistent one, conducted a characteristic analysis and distilled knowledge from real-world examples and the taxonomy. Our UIGuard consists of two components, Property Extraction and Knowledge-Driven Dark Pattern Checker. We collected the first dark pattern dataset, which contains 4,999 benign UIs and 1,353 malicious UIs of 1,660 instances spanning 1,023 mobile apps. Our system achieves a superior performance in detecting dark patterns (micro averages: 0.82 in precision, 0.77 in recall, 0.79 in F1 score). A user study involving 58 participants further shows that \tool{} significantly increases users' knowledge of dark patterns.

cs.HC↗

arXiv2023

Silent Vulnerable Dependency Alert Prediction with Vulnerability Key Aspect Explanation

Due to convenience, open-source software is widely used. For beneficial reasons, open-source maintainers often fix the vulnerabilities silently, exposing their users unaware of the updates to threats. Previous works all focus on black-box binary detection of the silent dependency alerts that suffer from high false-positive rates. Open-source software users need to analyze and explain AI prediction themselves. Explainable AI becomes remarkable as a complementary of black-box AI models, providing details in various forms to explain AI decisions. Noticing there is still no technique that can discover silent dependency alert on time, in this work, we propose a framework using an encoder-decoder model with a binary detector to provide explainable silent dependency alert prediction. Our model generates 4 types of vulnerability key aspects including vulnerability type, root cause, attack vector, and impact to enhance the trustworthiness and users' acceptance to alert prediction. By experiments with several models and inputs, we confirm CodeBERT with both commit messages and code changes achieves the best results. Our user study shows that explainable alert predictions can help users find silent dependency alert more easily than black-box predictions. To the best of our knowledge, this is the first research work on the application of Explainable AI in silent dependency alert prediction, which opens the door of the related domains.

cs.CR↗

arXiv2021

Generating Informative CVE Description From ExploitDB Posts by Extractive Summarization

ExploitDB is one of the important public websites, which contributes a large number of vulnerabilities to official CVE database. Over 60\% of these vulnerabilities have high- or critical-security risks. Unfortunately, over 73\% of exploits appear publicly earlier than the corresponding CVEs, and about 40\% of exploits do not even have CVEs. To assist in documenting CVEs for the ExploitDB posts, we propose an open information method to extract 9 key vulnerability aspects (vulnerable product/version/component, vulnerability type, vendor, attacker type, root cause, attack vector and impact) from the verbose and noisy ExploitDB posts. The extracted aspects from an ExploitDB post are then composed into a CVE description according to the suggested CVE description templates, which is must-provided information for requesting new CVEs. Through the evaluation on 13,017 manually labeled sentences and the statistically sampling of 3,456 extracted aspects, we confirm the high accuracy of our extraction method. Compared with 27,230 reference CVE descriptions. Our composed CVE descriptions achieve high ROUGH-L (0.38), a longest common subsequence based metric for evaluating text summarization methods.

cs.LG↗

arXiv2020

Task-Oriented API Usage Examples Prompting Powered By Programming Task Knowledge Graph

Programming tutorials are often created to demonstrate programming tasks with code examples. However, our study of Stack Overflow questions reveals the low utilization of high-quality programming tutorials, which is caused task description mismatch and code information overload. Document search can find relevant tutorial documents, but they often cannot find specific programming actions and code solutions relevant to the developers' task needs. The recently proposed activity-centric search over knowledge graph supports direct search of programming actions, but it has limitations in action coverage, natural language based task search, and coarse-grained code example recommendation. In this work, we enhance action coverage in knowledge graph with actions extracted from comments in code examples and more forms of activity sentences. To overcome the task description mismatch problem, we develop a code matching based task search method to find relevant programming actions and code examples to the code under development. We integrate our knowledge graph and task search method in the IDE, and develop an observe-push based tool to prompt developers with task-oriented API usage examples. To alleviate the code information overload problem, our tool highlights programming action and API information in the prompted tutorial task excerpts and code examples based on the underlying knowledge graph. Our evaluation confirms the high quality of the constructed knowledge graph, and show that our code matching based task search can recommend effective code solutions to programming issues asked on Stack Overflow. A small-scale user study demonstrates that our tool is useful for assisting developers in finding and using relevant programming tutorials in their programming tasks.

cs.SE↗