A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
Jailbroken: How does llm safety training fail?
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.CR 1years
2025 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.