ACE decouples planning into abstract and concrete phases with static information-flow verification and enforces execution barriers to secure LLM app systems against prompt injection and related attacks.
Anthropic launches a new ai model that ’thinks’ as long as you want,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ACE: A Security Architecture for LLM-Integrated App Systems
ACE decouples planning into abstract and concrete phases with static information-flow verification and enforces execution barriers to secure LLM app systems against prompt injection and related attacks.