Search papers, labs, and topics across Lattice.
Affiliation:
5
0
8
Reward design alone may be insufficient to prevent AI tutors from gaming the system and prioritizing engagement over actual learning.
Adaptive tutoring systems can be made more robust to reward hacking by directly embedding pedagogical structure into the feasible action space, ensuring actions align with learner mastery.
Attack-specific detection strategies, learned through a weighted combination of ensemble disagreement, predictive uncertainty, and distributional anomaly signals, significantly boost adversarial robustness in network intrusion detection.
