2 papers
cs.AI2026
Implementation of a Metacognition Framework for Self-Awareness and Self-Regulation in Ensembles of LLMs
Charles Courchaine, Ricky J. Sethi, Hefei Qiu
Large Language Models (LLMs) are notorious for struggling with assessing their own uncertainty, detecting knowledge conflicts, or recognizing when problems exceed their expertise;…
cs.CR2026
Triosecuris: Formally Verified Protection Against Speculative Control-Flow Hijacking
Jonathan Baumann, Yonghyun Kim, Yan Farba +2
This paper introduces Triosecuris, a formally verified defense against Spectre BTB, RSB, and PHT that combines CET-style hardware-assisted control-flow integrity with compiler-inse…