Xiaofei Xie
YOU?
Author Swipe
View article: Bridging the Digital Gradient: How Digital Literacy and Information Perception Shape Innovation and Entrepreneurship Across Urban, County and Township Students
Bridging the Digital Gradient: How Digital Literacy and Information Perception Shape Innovation and Entrepreneurship Across Urban, County and Township Students Open
Background: In China, a paradox has emerged: while the digital access gap narrows, a pronounced digital gradient—a sequential decline in outcomes from urban to county to township students—persists in innovation and entrepreneurship. This s…
View article: Diagnosing Failure Root Causes in Platform-Orchestrated Agentic Systems: Dataset, Taxonomy, and Benchmark
Diagnosing Failure Root Causes in Platform-Orchestrated Agentic Systems: Dataset, Taxonomy, and Benchmark Open
Agentic systems consisting of multiple LLM-driven agents coordinating through tools and structured interactions, are increasingly deployed for complex reasoning and problem-solving tasks. At the same time, emerging low-code and template-ba…
View article: Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning Open
Active learning(AL), which serves as the representative label-efficient learning paradigm, has been widely applied in resource-constrained scenarios. The achievement of AL is attributed to acquisition functions, which are designed for iden…
View article: Gradients as An Action: Towards Communication-Efficient Federated Recommender Systems via Adaptive Action Sharing
Gradients as An Action: Towards Communication-Efficient Federated Recommender Systems via Adaptive Action Sharing Open
As a promising privacy-aware collaborative model training paradigm, Federated Learning (FL) is becoming popular in the design of distributed recommender systems. However, Federated Recommender Systems (FedRecs) greatly suffer from two majo…
View article: The role of mast cells in allergic rhinitis
The role of mast cells in allergic rhinitis Open
Introduction In recent decades, mast cells and their mediators have been increasingly recognized as central players in the pathogenesis of allergic rhinitis (AR), a complex chronic nasal disease characterized by pathological changes influe…
View article: Understanding the Supply Chain and Risks of Large Language Model Applications
Understanding the Supply Chain and Risks of Large Language Model Applications Open
The rise of Large Language Models (LLMs) has led to the widespread deployment of LLM-based systems across diverse domains. As these systems proliferate, understanding the risks associated with their complex supply chains is increasingly im…
View article: MoDitector: Module-Directed Testing for Autonomous Driving Systems
MoDitector: Module-Directed Testing for Autonomous Driving Systems Open
Testing Autonomous Driving Systems (ADSs) is crucial for ensuring their safety, reliability, and performance. Despite numerous testing methods available that can generate diverse and challenging scenarios to uncover potential vulnerabiliti…
View article: CAShift: Benchmarking Log-Based Cloud Attack Detection under Normality Shift
CAShift: Benchmarking Log-Based Cloud Attack Detection under Normality Shift Open
With the rapid advancement of cloud-native computing, securing cloud environments has become an important task. Log-based Anomaly Detection (LAD) is the most representative technique used in different systems for attack detection and safet…
View article: VulStamp: Vulnerability Assessment using Large Language Model
VulStamp: Vulnerability Assessment using Large Language Model Open
Although modern vulnerability detection tools enable developers to efficiently identify numerous security flaws, indiscriminate remediation efforts often lead to superfluous development expenses. This is particularly true given that a subs…
View article: TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis
TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis Open
Text-to-image (T2I) models have significantly advanced in producing high-quality images. However, such models have the ability to generate images containing not-safe-for-work (NSFW) content, such as pornography, violence, political content…
View article: TensorJSFuzz: Effective Testing of Web-Based Deep Learning Frameworks via Input-Constraint Extraction
TensorJSFuzz: Effective Testing of Web-Based Deep Learning Frameworks via Input-Constraint Extraction Open
View article: Enmob: Unveil the Behavior with Multi-flow Analysis of Encrypted App Traffic
Enmob: Unveil the Behavior with Multi-flow Analysis of Encrypted App Traffic Open
In the contemporary digital landscape, mobile applications have become the predominant conduit for internet connectivity and daily tasks. Simultaneously, the advent of application encryption technology has safeguarded users’ privacy. Howev…
View article: MultiSFL: Towards Accurate Split Federated Learning via Multi-Model Aggregation and Knowledge Replay
MultiSFL: Towards Accurate Split Federated Learning via Multi-Model Aggregation and Knowledge Replay Open
Although Split Federated Learning (SFL) effectively enables knowledge sharing among resource-constrained clients, it suffers from low training performance due to the neglect of data heterogeneity and catastrophic forgetting problems. To ad…
View article: Understanding Codebase like a Professional! Human-AI Collaboration for Code Comprehension
Understanding Codebase like a Professional! Human-AI Collaboration for Code Comprehension Open
Understanding an unfamiliar codebase is an essential task for developers in various scenarios, such as during the onboarding process. Existing studies have shown that LLMs often fail to support users in understanding code structures or to …
View article: A real-world pharmacovigilance study of omalizumab using disproportionality analysis in the FDA adverse drug events reporting system database
A real-world pharmacovigilance study of omalizumab using disproportionality analysis in the FDA adverse drug events reporting system database Open
Omalizumab is a biologic agent used in the management of allergic conditions, including asthma and urticaria. Although the efficacy of omalizumab has been well established, its safety profile is primarily derived from clinical trials with …
View article: <i>ContrastRepair</i> : Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs
<i>ContrastRepair</i> : Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs Open
Automated Program Repair (APR) aims to automatically generate patches for rectifying software bugs. Recent strides in Large Language Models (LLM), such as ChatGPT, have yielded encouraging outcomes in APR, especially within the conversatio…
View article: MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation Open
View article: Optimized Application of CGA-SVM in Tight Reservoir Horizontal Well Production Prediction
Optimized Application of CGA-SVM in Tight Reservoir Horizontal Well Production Prediction Open
Horizontal well production prediction is crucial for the efficient development of tight reservoirs. However, owing to the complexity of the parameters affecting horizontal well production, improving the prediction accuracy has always been …
View article: Activation of TGF-β Smad Signaling Promotes Temporomandibular Joint Injury Repair in Aged Rats
Activation of TGF-β Smad Signaling Promotes Temporomandibular Joint Injury Repair in Aged Rats Open
View article: Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning
Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning Open
Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has proveided explanations for the actions or states of agents, yet falls short in understanding the black…
View article: DriveTester: A Unified Platform for Simulation-Based Autonomous Driving Testing
DriveTester: A Unified Platform for Simulation-Based Autonomous Driving Testing Open
Simulation-based testing plays a critical role in evaluating the safety and reliability of autonomous driving systems (ADSs). However, one of the key challenges in ADS testing is the complexity of preparing and configuring simulation envir…
View article: NebulaFL: Effective Asynchronous Federated Learning for JointCloud Computing
NebulaFL: Effective Asynchronous Federated Learning for JointCloud Computing Open
With advancements in AI infrastructure and Trusted Execution Environment (TEE) technology, Federated Learning as a Service (FLaaS) through JointCloud Computing (JCC) is promising to break through the resource constraints caused by heteroge…
View article: An Empirical Study of Vulnerability Detection using Federated Learning
An Empirical Study of Vulnerability Detection using Federated Learning Open
Although Deep Learning (DL) methods becoming increasingly popular in vulnerability detection, their performance is seriously limited by insufficient training data. This is mainly because few existing software organizations can maintain a c…
View article: Large Language Model Supply Chain: Open Problems From the Security Perspective
Large Language Model Supply Chain: Open Problems From the Security Perspective Open
Large Language Model (LLM) is changing the software development paradigm and has gained huge attention from both academia and industry. Researchers and developers collaboratively explore how to leverage the powerful problem-solving ability…
View article: A Comprehensive Study on Static Application Security Testing (SAST) Tools for Android
A Comprehensive Study on Static Application Security Testing (SAST) Tools for Android Open
To identify security vulnerabilities in Android applications, numerous static application security testing (SAST) tools have been proposed. However, it poses significant challenges to assess their overall performance on diverse vulnerabili…
View article: An Empirical Study to Evaluate AIGC Detectors on Code Content
An Empirical Study to Evaluate AIGC Detectors on Code Content Open
View article: Demo2Test: Transfer Testing of Agent in Competitive Environment with Failure Demonstrations
Demo2Test: Transfer Testing of Agent in Competitive Environment with Failure Demonstrations Open
The competitive game between agents exists in many critical applications, such as military unmanned aerial vehicles. It is urgent to test these agents to reduce the significant losses caused by their failures. Existing studies mainly are t…
View article: How Effective Are They? Exploring Large Language Model Based Fuzz Driver Generation
How Effective Are They? Exploring Large Language Model Based Fuzz Driver Generation Open
View article: Enhancing Multi-agent System Testing with Diversity-Guided Exploration and Adaptive Critical State Exploitation
Enhancing Multi-agent System Testing with Diversity-Guided Exploration and Adaptive Critical State Exploitation Open
View article: Bugs in Pods: Understanding Bugs in Container Runtime Systems
Bugs in Pods: Understanding Bugs in Container Runtime Systems Open