A competition report showing that white-box membership inference attacks on code LLMs mostly fail (AUC ~0.56–0.61) except for one structure-aware method (SERSEM, AUC ~0.77) that generalizes to a held-out model.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Poisoned Chalice of LLM Evaluation Report
A competition report showing that white-box membership inference attacks on code LLMs mostly fail (AUC ~0.56–0.61) except for one structure-aware method (SERSEM, AUC ~0.77) that generalizes to a held-out model.