A locally hosted 8B language model closed an autonomous observe-decide-act attack loop against a vulnerable target but completed only 10.9% of tasks, showing architectural feasibility without operational reliability.
Google Developers Blog (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Tiny Enough to Break In: Agentic Remote Access Trojans Powered by Small Language Models
A locally hosted 8B language model closed an autonomous observe-decide-act attack loop against a vulnerable target but completed only 10.9% of tasks, showing architectural feasibility without operational reliability.