6 papers
SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses
Hanbin Hong, Shuang Wu, Shuya Feng +6
Large Language Models (LLMs) are increasingly used as interfaces to information, code, and real-world services, making prompt-level security failures a practical concern. Although…
Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning
Shenao Yan, Shimaa Ahmed, Shan Jin +4
Code generation large language models (LLMs) are increasingly integrated into modern software development workflows. Recent work has shown that these models are vulnerable to backd…
Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
Nima Naderloui, Shenao Yan, Binghui Wang +4
Machine unlearning focuses on efficiently removing specific data from trained models, addressing privacy and compliance concerns with reasonable costs. Although exact unlearning en…
GALOT: Generative Active Learning via Optimizable Zero-shot Text-to-image Generation
Hanbin Hong, Shenao Yan, Shuya Feng +2
Active Learning (AL) represents a crucial methodology within machine learning, emphasizing the identification and utilization of the most informative samples for efficient model tr…
Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence
Shuya Feng, Meisam Mohammady, Hanbin Hong +4
Differentially private federated learning (DP-FL) is a promising technique for collaborative model training while ensuring provable privacy for clients. However, optimizing the tra…
An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection
Shenao Yan, Shen Wang, Yue Duan +4
Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fin…