LWLulu Wang

Lulu Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lulu Wang has a total of 47 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Litmus: Evaluating the Resilience of Blockchain-Enabled Software Systems for Supply Chains via Architecture Modeling and Chaos Injection

    by Can Zhao, Bixin Li, Lulu Wang, Li Liao, Ying Zhou

    Resilience is vital to blockchain-enabled software systems for supply chains (ChainFusion) and enables them to automatically adapt and continue providing their service when adverse situations occur. Since the notion of resilience in ChainFusion encompasses both the characteristics of a blockchain-enabled software system and the features of supply chains, complex trade-offs often exist among its resilience metrics. Furthermore, while blockchain technology provides novel mechanisms for enhancing resilience, it also introduces new resilience-related challenges. When evaluating the resilience, it is crucial to evaluate the impact of blockchain technology on resilience. We propose Litmus, a method for evaluating the resilience of ChainFusion. Litmus first models the system architecture using activity diagrams and extracts the minimal paths of the business process. Litmus then evaluates the resilience and outputs resilience issues by continuously injecting chaos into the system and monitoring variations in system state resilience curve. We assess the quality of Litmus by comparison with related work and through ablation experiments. We conduct case studies on a shipbuilding supply chain to evaluate the effectiveness of Litmus. Litmus identifies three previously unknown potential resilience issues.

  • Open Access

    Rethinking LLM-aided RTL Code Optimization via Timing Logic Metamorphosis

    by Zhihao Xu, Bixin Li, Ran Yan, Lulu Wang, Yongqiang Tian

    Register Transfer Level (RTL) code optimization is critical for meeting performance and power budgets in Field-Programmable Gate Array (FPGA) design. Traditional approaches depend on expert knowledge or heuristics, which are time-consuming and error-prone. Therefore, recent research has explored using Large Language Models (LLMs) for RTL code optimization and providing initial evidence of their potential. However, the capabilities and limitations of LLMs in RTL code optimization have not been systematically assessed, especially for RTL with complex timing logic. Moreover, these studies cannot distinguish whether improvements come from genuine reasoning or merely reproducing memorized patterns from training data. To address these problems, we present a metamorphic testing-based evaluation method and a companion benchmark to measure the effectiveness of LLM-aided RTL code optimization. Our key idea is that optimization effectiveness should be consistent across RTL descriptions that are semantically equivalent. We first build a benchmark suite covering four domains (logic operations, datapaths, timing control flow, and clock domains). We then apply domain-specific transformations to produce semantically equivalent RTL code with different code forms. We assess each method by applying it to both the original and the transformed code, synthesizing them with the same flow, and comparing the synthesis results. Through extensive experiments, our results show that LLM-aided methods effectively optimize logic operations and data paths, achieving lower or stable wire counts and area with delays near baseline. For timing control flow and clock domains, the gains are limited, and structural ratios often rise. Larger code size also increases the chance of incorrect rewrites, especially in timing and cross-domain designs. We further explore the application of prompt engineering include few shot examples and Chain-of-Thought (CoT), to improve RTL code optimization. Based on these results, we discuss practical directions and give concrete suggestions for using LLMs in RTL optimization.

  • Open Access

    Combining LLM-Based Semantic Analysis with Lightweight Deep Learning for Smart Contract Vulnerability Detection

    by Shuo Zhang, Zecheng Li, Shudan Lin, Jiahai Zhang, Yuheng Zhou, Lulu Wang, Bixin Li

    Smart contracts have become an integral part of most modern blockchain systems, playing a pivotal role in their operation. However, security vulnerabilities in smart contracts can lead to significant financial losses. Given the remarkable capabilities of Large Language Models (LLMs) in code understanding and analysis, it is worthwhile to explore how state-of-the-art LLMs can enhance the detection of smart contract vulnerabilities.In this paper, we propose a collaborative detection method that combines semantic analysis performed by LLMs with a lightweight deep learning model. Rather than relying on LLMs for direct vulnerability detection, we engineer tailored prompts that guide the model to perform multidimensional semantic analysis of smart contract code, yielding structured insights. Subsequently, we utilize a pre-trained CodeBERT model to encode these insights into dense feature vectors, which facilitate vulnerability detection via a lightweight, efficient deep learning classifier.Experiments on real-world smart contract datasets show that our approach achieves accuracy rates of 99.85%, 93.2%, 99.33%, and 98.13% for four types of vulnerabilities: reentrancy, timestamp dependency, unchecked external calls, and strict equality to Ether, respectively. These results demonstrate that the synergy between LLM-based semantic analysis and a lightweight detection model offers a novel and effective solution for automated smart contract auditing. This approach requires no expert knowledge, remains intuitive and easy to implement, and exhibits strong scalability.

  • A Survey of Blockchain Privacy Protection in Intra-Chain and Cross-Chain Scenarios: State-of-the-Art, Challenges, and Future Work

    by Dongyu Cao, Bixin Li, Lulu Wang, Huijie Zhang, Yong Wang

    The rapid development of blockchain has spurred the emergence of programmable currency, finance, and society. However, blockchains are subject to severe privacy issues such as deanonymization, transaction linkability, and malicious contracts. Numerous studies in academia and industry have been dedicated to blockchain privacy protection. However, existing surveys tend to be limited in scope, often addressing only intra-chain privacy while neglecting cross-chain concerns and providing incomplete coverage of privacy protection methods. To facilitate interested researchers to comprehend the research field better, this paper presents a comprehensive survey about blockchain privacy protection utilizing a mapping study. We provide a detailed analysis of three types of privacy information, their corresponding privacy threats, four categories of privacy-preserving methods, and validation methods in intra-chain and cross-chain scenarios. We also summarize some typical applications of blockchain where privacy protection is crucial. Moreover, we highlight some deficiencies of the current study, and discuss challenges and future research directions in this field.


  • Refined Program Slicing Based on Online Redundancy Removal

    by Jianming Chang, Lulu Wang, Li Liao, Ying Zhou

    Program slicing is widely used in software engineering to support program comprehension, debugging, and testing. Most existing slicing techniques generate slices through reachability analysis over dependence graphs. However, such approaches do not distinguish between essential dependences and redundant dependences, causing many statements that do not actually affect the slicing criterion to be included in the slice. This phenomenon leads to slice bloat and makes it difficult for developers to identify the code that truly affects the slicing criterion. To address this problem, this paper introduces the concept of Redundant Code for a Slice (RCS), which refers to statements that appear in a slice due to dependence propagation but do not contribute to the values computed at the slicing criterion. We further identify six common types of RCS in real-world programs and propose a Marked System Dependence Graph (MSDG) to explicitly represent redundant and non-redundant dependences in the dependence graph. Based on MSDG, we present a refined program slicing algorithm, called RPS, which removes RCS online during dependence traversal and produces more concise slices that preserve the semantics of the slicing criterion. We evaluate RPS against traditional two-phase slicing, type slicing, and dynamic slicing on 20 open-source projects. The results show that RPS can reduce slice size by 49%, 45%, and 11% compared with the three baselines, respectively. In addition, we apply RPS to bug localization on the Defects4J benchmark. The results show that RPS can assist in locating 79% of bugs while reducing 20% of the slice size compared with type slicing.

  • Top Cited Papers

    Bridging Bug Localization and Issue Fixing: A Hierarchical Localization Framework Leveraging Large Language Models

    by Jianming Chang, Xin Zhou, Lulu Wang, David Lo, Bixin Li, Lulu Lulu

    Automated issue fixing is a critical task in software debugging and has recently garnered significant attention from academia and industry. However, existing fixing techniques predominantly focus on the repair phase, often overlooking the importance of improving the preceding bug localization phase. As a foundational step in issue fixing, bug localization plays a pivotal role in determining the overall effectiveness of the entire process. To enhance the precision of issue fixing by accurately identifying bug locations in large-scale projects, this paper presents BugCerberus, the first hierarchical bug localization framework powered by three customized large language models. First, BugCerberus analyzes intermediate representations of bug-related programs at file, function, and statement levels and extracts bug-related contextual information from the representations. Second, BugCerberus designs three customized LLMs at each level using bug reports and contexts to learn the patterns of bugs. Finally, BugCerberus hierarchically searches for bug-related code elements through well-tuned models to localize bugs at three levels. With BugCerberus, we further investigate the impact of bug localization on the issue fixing. We evaluate BugCerberus on the widely-used benchmark SWE-bench-lite. The experimental results demonstrate that BugCerberus outperforms all baselines. Specifically, at the fine-grained statement level, BugCerberus surpasses the state-of-the-art in Top-N (N=1, 3, 5, 10) by 16.5%, 5.4%, 10.2%, and 23.1%, respectively. Moreover, in the issue fixing experiments, BugCerberus improves the fix rate of the existing issue fixing approach Agentless by 17.4% compared to the best baseline, highlighting the significant impact of enhanced bug localization on automated issue fixing.


  • ZKVeil: A Privacy-Preserving Compliance Verification Scheme for Blockchain-Enabled Supply Chain Transactions

    by Dongyu Cao, Bixin Li, Huijie Zhang, Yong Wang, Lulu Wang

    Blockchain technology improves supply chain management by ensuring the immutability of transaction records and facilitating process tracking. However, the transparency of blockchain raises significant privacy concerns, as sensitive information such as buyer and supplier qualifications, product specifications, and transaction amounts is often exposed. Compliance verification, which needs access to specific sensitive data for compliance checks, becomes challenging in blockchain-based privacy-preserving supply chains. This paper introduces ZKVeil, an innovative scheme utilizing zero-knowledge proof technology to maintain the confidentiality of sensitive information while ensuring compliance verification. Additionally, ZKVeil uses decentralized identifiers and verifiable credentials to ensure the authenticity of transaction data. A theoretical security analysis demonstrates the effectiveness of ZKVeil in safeguarding real sensitive data and ensuring compliance with regulations. To evaluate the performance of our scheme, we implement ZKVeil on a private blockchain of 100 nodes. Taking the shipbuilding supply chain transaction as an example, the experimental results demonstrate that ZKVeil incurs low gas consumption, execution time, and memory overhead.