arXiv subjects

Xia Feng

Publications and source records attributed to Xia Feng.

12 recordsLinked to original sources

arXiv2026

Understanding before Naming! Enhancing LLM-based Method Name Prediction with Code Summarization

Method names are critical to software quality, affecting code comprehensibility, maintainability, and developer collaboration. However, manually designing meaningful method names is challenging. Method Name Prediction (MNP), which automatically generates method names from code snippets, has recently attracted attention. Although large language models (LLMs) show promising performance for MNP, two challenges remain. First, existing evaluations mainly rely on token similarity metrics, which often fail to reflect human judgments of semantic quality. Second, current LLM-based MNP methods usually generate names through direct code-to-name mapping, which differs from the human process of understanding functionality before naming. To address these challenges, we conduct empirical studies on LLM-based evaluation and MNP strategies. We compare 6 metric-based evaluators, 5 LLM-based evaluators, and 6 human evaluators. Results show that LLM-based evaluators, especially DeepSeek-based evaluators, are more consistent with human judgments than traditional metrics. We further compare direct generation and summarization-and-refinement strategies. Results indicate that summarization and refinement generally improve the semantic quality of generated names. Case studies reveal three limitations: inaccurate summaries, semantic misalignment, and close semantic scores. Based on these findings, we propose SMNP, an MNP approach combining MNP-oriented summarization and chain-of-thought enhanced refinement. Experiments on 5 LLMs and 2 datasets demonstrate the effectiveness and robustness of SMNP.

cs.SE↗

arXiv2026

Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines

Coding agents are increasingly integrated into system operations, where their tool use can directly modify project artifacts, execution environments, and the underlying system. For example, if a coding agent inserts a hook into a system startup or configuration script, that change can persist after the interaction, be triggered later, and abuse delegated user or system privileges to modify the system. This makes security testing a system problem: the key question is not only what the agent says, but what it actually does to the surrounding environment. We present an execution-grounded red-team testing framework for probing this execution-layer security boundary using observable sandbox evidence, including tool invocations, runtime traces, and file-system diffs. Our framework embeds target unsafe operations into routine software engineering workloads, including unit testing, regression testing, crash reproduction, and validation, and uses an execution oracle to guide refinement when an initial probe is rejected or fails. Across multiple agent frameworks and model backbones, our red-team workload reformulation substantially increases verified unsafe execution, reaching 73.61% on code carriers and 53.93% on text carriers. These results show that coding agents in system operations remain insecure under task disguise: once risky intent is hidden inside plausible engineering tasks, the agent can be induced to carry out unsafe actions on the surrounding system. More broadly, coding agents in system operations still demand stronger security testing and safeguards.

cs.AI↗

arXiv2026

Probing Privacy Leaks in LLM-based Code Generation via Test Generation

The widespread availability of large-scale code datasets has fueled the rapid development of large language models (LLMs) for code-related tasks. These datasets may include sensitive personally identifiable information (PII), which can lead to privacy leakage when LLMs memorize and reproduce it. However, existing privacy-leakage detection methods rely on ad-hoc prompt construction (manually or automatically designed). Therefore, they do not adequately approximate the real-world contexts in which PII appears in code corpora, making it difficult to extract realistic privacy leakage. In this paper, we propose a pipeline that simulates practical privacy-related code generation scenarios and adopts a test-driven strategy to elicit the memorized information from the generated test cases. We further introduce an automatically constructed privacy feature library that replaces manual prompt engineering by providing realistic templates and examples to guide test case generation. Large-scale experiments on 5 widely used LLMs show that our pipeline exposes more confirmed privacy leakage, achieving a 2.56 times increase in detected leakage compared to existing baselines.

cs.SE↗

arXiv2025

Capturing Rich Behavior Representations: A Dynamic Action Semantic-Aware Graph Transformer for Video Captioning

Existing video captioning methods merely provide shallow or simplistic representations of object behaviors, resulting in superficial and ambiguous descriptions. However, object behavior is dynamic and complex. To comprehensively capture the essence of object behavior, we propose a dynamic action semantic-aware graph transformer. Firstly, a multi-scale temporal modeling module is designed to flexibly learn long and short-term latent action features. It not only acquires latent action features across time scales, but also considers local latent action details, enhancing the coherence and sensitiveness of latent action representations. Secondly, a visual-action semantic aware module is proposed to adaptively capture semantic representations related to object behavior, enhancing the richness and accurateness of action representations. By harnessing the collaborative efforts of these two modules,we can acquire rich behavior representations to generate human-like natural descriptions. Finally, this rich behavior representations and object representations are used to construct a temporal objects-action graph, which is fed into the graph transformer to model the complex temporal dependencies between objects and actions. To avoid adding complexity in the inference phase, the behavioral knowledge of the objects will be distilled into a simple network through knowledge distillation. The experimental results on MSVD and MSR-VTT datasets demonstrate that the proposed method achieves significant performance improvements across multiple metrics.

cs.CV↗

arXiv2024

$\lambda$ and $\rho$ Regge trajectories for hidden bottom and charm tetraquarks $(Qq)(\bar{Q}\bar{q}')$

We propose the Regge trajectory relations for the heavy tetraquarks $(Qq)(\bar{Q}\bar{q}')$ $(Q=b,\,c;\,q,\,q'=u,\,d,\,s)$ with hidden bottom and charm. By employing the new relations, both the $\lambda$-trajectories and the $\rho$-trajectories for the tetraquarks $(Qq)(\bar{Q}\bar{q}')$ can be discussed. The masses of the $\lambda$-mode excited states and the $\rho$-mode excited states are estimated, and they agree with other theoretical predictions. We show that the behaviors of the $\rho$-trajectories are different from those of the $\lambda$-trajectories. The $\rho$-trajectories behave as $M{\sim}x_{\rho}^{1/2}$ $(x_{\rho}=n_r,\,l)$ while the $\lambda$-trajectories behave as $M{\sim}x_{\lambda}^{2/3}$ $(x_{\lambda}=N_r,\,L)$. Moreover, the Regge trajectory behaviors for other types of tetraquarks are investigated based on the spinless Salpeter equation. We show that both the $\lambda$-trajectories and the $\rho$-trajectories are concave downward in the $(M^2,\,x)$ plane. The Regge trajectories for the tetraquarks containing the light diquark and/or the light antidiquark also are concave in the $(M^2,\,x)$ plane when the masses of the light constituents are included and the confining potential is linear.

hep-ph↗

arXiv2024

Chu-ko-nu: A Reliable, Efficient, and Anonymously Authentication-Enabled Realization for Multi-Round Secure Aggregation in Federated Learning

Secure aggregation enables federated learning (FL) to perform collaborative training of clients from local gradient updates without exposing raw data. However, existing secure aggregation schemes inevitably perform an expensive fresh setup per round because each client needs to establish fresh input-independent secrets over different rounds. The latest research, Flamingo (S&P 2023), designed a share-transfer-based reusable secret key to support the server continuously performing multiple rounds of aggregation. Nevertheless, the share transfer mechanism it proposed can only be achieved with P probability, which has limited reliability. To tackle the aforementioned problems, we propose a more reliable and anonymously authenticated scheme called Chu-ko-nu for multi-round secure aggregation. Specifically, in terms of share transfer, Chu-ko-nu breaks the probability P barrier by supplementing a redistribution process of secret key components (the sum of all components is the secret key), thus ensuring the reusability of the secret key. Based on this reusable secret key, Chu-ko-nu can efficiently perform consecutive aggregation in the following rounds. Furthermore, considering the client identity authentication and privacy protection issue most approaches ignore, Chu-ko-nu introduces a zero-knowledge proof-based authentication mechanism. It can support clients anonymously participating in FL training and enables the server to authenticate clients effectively in the presence of various attacks. Rigorous security proofs and extensive experiments demonstrated that Chu-ko-nu can provide reliable and anonymously authenticated aggregation for FL with low aggregation costs, at least a 21.02% reduction compared to the state-of-the-art schemes.

cs.CR↗

arXiv2023

A Prompt Learning Framework for Source Code Summarization

(Source) code summarization is the task of automatically generating natural language summaries (also called comments) for given code snippets. Recently, with the successful application of large language models (LLMs) in numerous fields, software engineering researchers have also attempted to adapt LLMs to solve code summarization tasks. The main adaptation schemes include instruction prompting, task-oriented (full-parameter) fine-tuning, and parameter-efficient fine-tuning (PEFT). However, instruction prompting involves designing crafted prompts and requires users to have professional domain knowledge, while task-oriented fine-tuning requires high training costs, and effective, tailored PEFT methods for code summarization are still lacking. This paper proposes an effective prompt learning framework for code summarization called PromptCS. It no longer requires users to rack their brains to design effective prompts. Instead, PromptCS trains a prompt agent that can generate continuous prompts to unleash the potential for LLMs in code summarization. Compared to the human-written discrete prompt, the continuous prompts are produced under the guidance of LLMs and are therefore easier to understand by LLMs. PromptCS is non-invasive to LLMs and freezes the parameters of LLMs when training the prompt agent, which can greatly reduce the requirements for training resources. Our comprehensive experimental results show that PromptCS significantly outperforms instruction prompting schemes (including zero-shot learning and few-shot learning) on all four widely used metrics, and is comparable to the task-oriented fine-tuning scheme. In some base LLMs, e.g., StarCoderBase-1B and -3B, PromptCS even outperforms the task-oriented fine-tuning scheme. More importantly, the training efficiency of PromptCS is faster than the task-oriented fine-tuning scheme, with a more pronounced advantage on larger LLMs.

cs.SE↗

arXiv2023

Regge trajectories for the light diquarks

We attempt to present an unified description of the light meson spectra and the light diquark spectra by applying the Regge trajectory approach. However, we find that the direct application of the linear Regge trajectory formula for the light mesons and baryons fails. To address this issue, we fit the experimental data of light meson spectra and the light diquark spectra obtained by other theoretical approaches. By considering the light quark mass and the parameter $C$ in the Cornell potential, we provide a provisional Regge trajectory formula. We also crudely estimate the masses of the light diquarks $(ud)$, $(us)$, and $(ss)$, and find that they agree with other theoretical results. The diquark Regge trajectory not only becomes a new and very simple approach for estimating the spectra of the light diquarks, but also can explicitly show the behavior of the masses with respect to $l$ or $n_r$. Moreover, it is expected that the diquark Regge trajectory can provide a simple method for investigating the $\rho$-mode excitations of baryons, tetraquarks and pentaquarks containing diquarks.

hep-ph↗

arXiv2023

Regge trajectories for the heavy-light diquarks

We attempt to apply the Regge trajectory approach to the heavy-light diquarks composed of one heavy quark and one light quark. However, we find that the direct application of the usual Regge trajectory formula for the heavy-light mesons and baryons fails. In order to correctly estimate the masses of the heavy-light diquarks, it is needed to consider the light quark mass correction and the parameter $C$ in the Cornell potential within the Regge trajectory formula. By using the modified Regge trajectory formulas, we are able to estimate the masses of the heavy-light diquarks $(cu)$, $(cs)$, $(bu)$ and $(bs)$, which agree with other theoretical results. It is illustrated that the heavy-light diquarks satisfy the universal descriptions irrespective of heavy quark flavors, similar to other heavy-light systems such as the heavy-light mesons, the heavy-light baryons composed of one heavy quark (diquark) and one light diquark (quark), and the heavy-light tetraquarks composed of one heavy diquark (antidiquark) and one light antidiquark (diquark). The diquark Regge trajectory provides a new and very simple approach for estimating the spectra of the heavy-light diquarks.

hep-ph↗

arXiv2023

Regge trajectories for the doubly heavy diquarks

The concept of diquark is important for understanding hadron structure and high-energy particle reactions. We attempt to apply the Regge trajectory approach to the doubly heavy diquarks. We present a method for determining the parameters in the diquark Regge trajectory. The spectra of diquarks $(cc)$, $(bb)$, and $(bc)$ are obtained by using the {\rt} approach and are found to agree with other theoretical results. The diquark Regge trajectory becomes a new and very simple approach for estimating the spectra of diquarks.

hep-ph↗

arXiv2022

PBAG: A Privacy-Preserving Blockchain-based Authentication Protocol with Global-updated Commitment in IoV

Internet of Vehicles(IoV) is increasingly used as a medium to propagate critical information via establishing connections between entities such as vehicles and infrastructures. During message transmission, privacy-preserving authentication is considered as the first line of defence against attackers and malicious information. To achieve a more secure and stable communication environment, ever-increasing numbers of blockchain-based authentication schemes are proposed. At first glance, existing approaches provide robust architectures and achieve transparent authentication. However, in these schemes, verifiers must connect to the blockchain network in advance and accomplish the authentication with smart contracts, which prolongs the latency. To remedy this limit, we propose a privacy-preserving blockchain-based authentication protocol(PBAG), where Root Authority(RA) generates a unique evaluation proof corresponding to the issued certificate for each authorized vehicle. Meanwhile, RA broadcasts a public global commitment based on all valid certificates. Instead of querying certificates stored in the blockchain, the vehicle will be efficiently proved to be an authorized user by utilizing the global commitment through bilinear pairing. Moreover, our scheme can prevent vehicles equipped with invalid certificates from accomplishing the authentication, thus avoiding the time-consuming for checking Certificate Revocation List (CRL). Finally, our scheme provides privacy properties such as anonymity and unlinkability. It allows anonymous authentication based on evaluation proofs and achieves traceability of identity in the event of a dispute. The simulation demonstrates that the average time of verification is 0.36ms under the batch-enabled mechanism, outperforming existing schemes by at least 63.7%.

cs.CR↗

arXiv2018

Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey

Topic modeling is one of the most powerful techniques in text mining for data mining, latent data discovery, and finding relationships among data, text documents. Researchers have published many articles in the field of topic modeling and applied in various fields such as software engineering, political science, medical and linguistic science, etc. There are various methods for topic modeling, which Latent Dirichlet allocation (LDA) is one of the most popular methods in this field. Researchers have proposed various models based on the LDA in topic modeling. According to previous work, this paper can be very useful and valuable for introducing LDA approaches in topic modeling. In this paper, we investigated scholarly articles highly (between 2003 to 2016) related to Topic Modeling based on LDA to discover the research development, current trends and intellectual structure of topic modeling. Also, we summarize challenges and introduce famous tools and datasets in topic modeling based on LDA.

cs.IR↗