The paper argues that AI safety targets unintentional failures while AI security targets intentional attacks, and that both dimensions must be integrated to achieve trustworthy AI.
International AI safety report: The international scientific report on the safety of advanced AI
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
AI Safety vs. AI Security: Demystifying the Distinction and Boundaries
The paper argues that AI safety targets unintentional failures while AI security targets intentional attacks, and that both dimensions must be integrated to achieve trustworthy AI.