Publication archive
Publications
WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics
From User Operations to Agentic Automation: Toward Intent-Oriented Software in the LLM Era
AstraGame: Effective and Efficient VLM Agent Serving for Large-Scale Game Testing in an Industry Setting
When to Answer and When to Defer: A Decision Framework for Reliable Code Predictions
On-the-Fly Input Adaptation for Reliable Code Intelligence
Judge: Effective State Abstraction for Guiding Automated Web GUI Testing
Efficiency Robustness of Dynamic Deep Learning Systems
RVISmith: Fuzzing Compilers for RVV Intrinsics
An Investigation on Numerical Bugs in GPU Programs Towards Automated Bug Detection
Medusa: A Framework for Collaborative Development of Foundation Models with Automated Parameter Ownership Assignment
Foundation Model Engineering: Engineering Foundation Models Just as Engineering Software
Element-Aware Fine-Tuning of Vision-Language Models for Cost-Efficient GUI Testing in an Industrial Setting
Automatic Mathematic In-Context Example Generation for LLM Using Multi-Modal Consistency
TAOPT: Tool-Agnostic Optimization of Parallelized Automated Mobile UI Testing
LogLabeler: Towards Effective Acquisition of Log Labels in Industrial Log-Based Analysis
CodeImprove: Program Adaptation for Deep Code Models
MalScan: Android Malware Detection Based on Social-Network Centrality Analysis
Can you mimic me? Exploring the Use of Android Record & Replay Tools in Debugging
StdGEN: Semantic-Decomposed 3D Character Generation from Single Images
DPEfficR: a data and parameter efficient approach for training neural API recommendation model
LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models
Guardian: A Runtime Framework for LLM-based UI Exploration
Automated Testing Linguistic Capabilities of NLP Models
HateModerate: Testing Hate Speech Detectors against Content Moderation Policies
HawkEyes: Spotting and Evading Instruction Disalignments of LLMs
PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models
DeciX: Explain Deep Learning Based Code Generation Applications
WEFix: Intelligent Automatic Generation of Explicit Waits for Efficient Web End-to-End Flaky Tests
MENDNet: Just-in-time Fault Detection and Mitigation in AI Systems with Uncertainty Quantification and Multi-Exit Networks
IMPACT ANALYSIS OF INFERENCE TIME ATTACK OF PERCEPTION SENSORS ON AUTONOMOUS VEHICLES
RT-LM: Uncertainty-Aware Resource Management for Real-Time Inference of Language Models
DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization
SlothSpeech: Denial-of-service Attack Against Speech Recognition Models
AntiNODE: Evaluating Efficiency Robustness of Neural ODEs
Dynamic Neural Network is All You Need: Understanding the Robustness of Dynamic Mechanisms in Neural Networks
The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection
Dynamic Transformers Provide a False Sense of Efficiency
Contrastive Learning for Robust Android Malware Familial Classification
DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks
An Empirical Analysis of Compatibility Issues for Industrial Mobile Games
TestAug: A Framework for Augmenting Capability-based NLP Tests
NMTSloth: Understanding and Testing Efficiency Degradation of Neural Machine Translation Systems
Learning to Reverse DNNs from AI Programs Automatically
NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models
CorrGAN:Input Transformation Technique Against Natural Corruptions.
EREBA: Black-box Energy Testing of Adaptive Neural Networks
Detecting Topology Attacks against Graph Neural Networks
VulCNN: An Image-inspired Scalable Vulnerability Detection System
Vet: Identifying and Avoiding UI Exploration Tarpits
GLIB: Towards Automated Test Oracle for Graphically-Rich Applications
HomDroid: Detecting Android Covert Malware by Social-Network Homophily Analysis
WebEvo: Taming Web Application Evolution via Detecting Semantic Structure Change
An Empirical Analysis of UI-based Flaky Tests
UI-Based Flaky Tests Dataset
Acoustic fingerprint based smart mobiles indoor localization under dense NLOS environment
IntDroid: Android Malware Detection Based on API Intimacy Analysis
Database-Access Performance Antipatterns in Database-Backed Web Applications
SCDetector: Software Functional Clone Detection Based on Semantic Tokens Analysis
DENAS: Automated Rule Generation by Knowledge Extraction from Neural Networks
ILFO: Adversarial Attack on Adaptive Neural Networks
TextExerciser: Feedback-driven Text Input Exercising for Android Applications
MalScan: Fast Market-Wide Mobile Malware Scanning by Social-Network Centrality Analysis
Charting the Attack Surface of Trigger-Action IoT Platforms
REINAM: Reinforcement Learning for Input-Grammar Inference
Testing Untestable Neural Machine Translation: An Industrial Case
Detecting Failures of Neural Machine Translation in the Absence of Reference Translations
SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications
Property Inference Attacks on Deep Neural Networks using Permutation Invariant Representations
An Empirical Study of Android Test Generation Tools in Industrial Cases
A Large-Scale Empirical Study on Android Runtime Permission Rationale Messages
Mining Android App Description for Permission Requirements Recommendation
EnMobile: Entity-based Characterization and Analysis of Mobile Malware
Generating Regular Expressions from Natural Language Specifications: Are We There Yet?
Telemade: A Testing Framework for Learning-Based Malware Detection Systems.
Malware Detection in Adversarial Settings: Exploiting Feature Evolutions and Confusions in Android Apps
Automated Test Input Generation for Android: Towards Getting There in an Industrial Case
Towards Privacy-Preserving Mobile Apps: A Balancing Act.
Free for All! Assessing User Data Exposure to Advertising Libraries on Android
Automated Test Input Generation for Android: Are We Really There Yet in an Industrial Case?
Security Analytics for Mobile Apps: Achievements and Challenges.
AppContext: Differentiating Malicious and Benign Mobile App Behaviors Using Context
Improving Mobile Application Security via Bridging User Expectations and Application Behaviors.
WHYPER: Towards Automating Risk Assessment of Mobile Applications
A Grey-box Approach for Automated GUI-Model Generation of Mobile Applications
No publications match your search.