4 papers
Diagnose Before You Compress: Prediction-Independent Bottleneck Witness Refinement for LLM Serving Traces
Liming Liu, Chao Hu, Mingfei Lu +7
Production LLM serving generates millions of diverse requests, making full-trace replay across serving configurations increasingly expensive. Existing trace reduction methods mainl…
Inducing Vulnerable Code Generation in LLM Coding Assistants
Binqi Zeng, Quan Zhang, Chijin Zhou +3
Due to insufficient domain knowledge, LLM coding assistants often reference related solutions from the Internet to address programming problems. However, incorporating external inf…
QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems
Jinjing Shi, Zimeng Xiao, Heyuan Shi +2
Quantum Neural Network (QNN) combines the Deep Learning (DL) principle with the fundamental theory of quantum mechanics to achieve machine learning tasks with quantum acceleration.…
Human-Imperceptible Retrieval Poisoning Attacks in LLM-Powered Applications
Quan Zhang, Binqi Zeng, Chijin Zhou +3
Presently, with the assistance of advanced LLM application development frameworks, more and more LLM-powered applications can effortlessly augment the LLMs' knowledge with external…