4 papers
Preliminary Investigation into Uncertainty-Aware Attack Stage Classification
Alessandro Gaudenzi, Lorenzo Nodari, Lance Kaplan +3
Advanced Persistent Threats (APTs) represent a significant challenge in cybersecurity due to their prolonged, multi-stage nature and the sophistication of their operators. Traditio…
Learning Robust Reward Machines from Noisy Labels
Roko Parac, Lorenzo Nodari, Leo Ardon +3
This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM-driven R…
Assessing the Robustness of Intelligence-Driven Reinforcement Learning
Lorenzo Nodari, Federico Cerutti
Robustness to noise is of utmost importance in reinforcement learning systems, particularly in military contexts where high stakes and uncertain environments prevail. Noise and unc…
Adversarial Attacks to Reward Machine-based Reinforcement Learning
Lorenzo Nodari
In recent years, Reward Machines (RMs) have stood out as a simple yet effective automata-based formalism for exposing and exploiting task structure in reinforcement learning settin…