Logic-Layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems
Explores LPCI, a new security vulnerability in agentic AI, its lifecycle, attack methods, and proposed defenses.
Abstract: An incremental iterative Q-learning algorithm (IIQLA) is proposed to tackle the optimal secure control problem for cyber-physical systems under false data injection attacks. Within a ...
Abstract: This brief proposes a hierarchical predefined time optimal secondary control strategy for microgrid systems with external disturbances. Unlike traditional control methods, the key ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results