A two-stage attack claims to recover a black-box LLM's output projection from under 10k top-k logit queries and distill a compact clone, but the core matrix-completion step is not justified.
Leveraging large language models for integrated satellite-aerial-terrestrial networks: recent advances and future directions,
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
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation
A two-stage attack claims to recover a black-box LLM's output projection from under 10k top-k logit queries and distill a compact clone, but the core matrix-completion step is not justified.