9 papers
Compiling Large Multi-Modal Requirement Documents into Runnable Software Systems: From an Agentic Test-Driven Perspective
Weiyu Kong, Yun Lin, Xiwen Teoh +5
Large Language Models (LLMs) have significantly improved programming efficiency by translating natural language into code, yet their performance deteriorates when handling large-sc…
MINES: Explainable Anomaly Detection through Web API Invariant Inference
Wenjie Zhang, Yun Lin, Chun Fung Amos Kwok +5
Detecting the anomalies of web applications, important infrastructures for running modern companies and governments, is crucial for providing reliable web services. Many modern web…
CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels
Xing Ma, Yangjie Zhou, Wu Sun +6
Efficient CUDA implementations of attention mechanisms are critical to modern deep learning systems, yet supporting diverse and evolving attention variants remains challenging. Exi…
WebTestPilot: Agentic End-to-End Web Testing against Natural Language Specification by Inferring Oracles with Symbolized GUI Elements
Xiwen Teoh, Yun Lin, Duc-Minh Nguyen +3
Visual language model (VLM) agents show great promise in automating end-to-end (E2E) web testing against requirements in natural language. However, the probabilistic nature of lang…
DRIP: Defending Prompt Injection via Token-wise Representation Editing and Residual Instruction Fusion
Ruofan Liu, Yun Lin, Zhiyong Huang +1
Large language models (LLMs) are increasingly integrated into IT infrastructures, where they process user data according to predefined instructions. However, conventional LLMs rema…
PiMRef: Detecting and Explaining Ever-evolving Spear Phishing Emails with Knowledge Base Invariants
Ruofan Liu, Yun Lin, Silas Yeo Shuen Yu +3
Phishing emails are a critical component of the cybercrime kill chain due to their wide reach and low cost. Their ever-evolving nature renders traditional rule-based and feature-en…