Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
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.…
cs.CR2024
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…