Introduces ePCA framework using neural-symbolic isolation to force agents to formalize intentions as logical constraints, claiming zero attack success and false positive rates in tested scenarios.
Title resolution pending
3 Pith papers cite this work, alongside 20 external citations. Polarity classification is still indexing.
3
Pith papers citing it
20
external citations · external index
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
AI security and alignment cannot achieve full robustness because any sufficiently powerful AI inherits incompleteness-style limitations from formal systems.
citing papers explorer
-
Provably Secure Agent Guardrail
Introduces ePCA framework using neural-symbolic isolation to force agents to formalize intentions as logical constraints, claiming zero attack success and false positive rates in tested scenarios.
-
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
-
Robust AI Security and Alignment: A Sisyphean Endeavor?
AI security and alignment cannot achieve full robustness because any sufficiently powerful AI inherits incompleteness-style limitations from formal systems.