6 papers
INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems
Thuy Dung Nguyen, Jingyi Guo, Rana Seda Dubauskas +3
LLM-based agents increasingly execute long-horizon, end-to-end workflows involving shell commands, code modification, dependency installation, and interaction with remote services.…
Modeling Spectral Energy Shifts in Spatio-Temporal Graph Anomaly Detection
Yilin Liu, Hongchao Zhang, Taylor T. Johnson +2
Graph anomaly detection methods aim to distinguish anomalous nodes. While prior methods characterize anomalies through increased variation in the spectral energy distributions, the…
PBP: Post-training Backdoor Purification for Malware Classifiers
Dung Thuy Nguyen, Ngoc N. Tran, Taylor T. Johnson +1
In recent years, the rise of machine learning (ML) in cybersecurity has brought new challenges, including the increasing threat of backdoor poisoning attacks on ML malware classifi…
LOGSAFE: Logic-Guided Verification for Trustworthy Federated Time-Series Learning
Dung Thuy Nguyen, Ziyan An, Taylor T. Johnson +2
This paper introduces LOGSAFE, a defense mechanism for federated learning in time series settings, particularly within cyber-physical systems. It addresses poisoning attacks by mov…
PARDON: Privacy-Aware and Robust Federated Domain Generalization
Dung Thuy Nguyen, Taylor T. Johnson, Kevin Leach
Federated Learning (FL) shows promise in preserving privacy and enabling collaborative learning. However, most current solutions focus on private data collected from a single domai…
Formal Logic Enabled Personalized Federated Learning Through Property Inference
Ziyan An, Taylor T. Johnson, Meiyi Ma
Recent advancements in federated learning (FL) have greatly facilitated the development of decentralized collaborative applications, particularly in the domain of Artificial Intell…