Any deterministic prompt filter for code LLMs has a provable mutual-information lower bound of at least 0.84 nats on HumanEval and 1.20 nats on MBPP under pass-only acceptance, with no tested filter achieving zero proxy-axis leakage.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Replication finds Java security API misuse persists in current LLMs but is reduced by external knowledge in a model-dependent manner.
citing papers explorer
-
The Security Budget of Code-LLM Prompt Hardening: Provable Limits Under Pass-Only Acceptance
Any deterministic prompt filter for code LLMs has a provable mutual-information lower bound of at least 0.84 nats on HumanEval and 1.20 nats on MBPP under pass-only acceptance, with no tested filter achieving zero proxy-axis leakage.
-
R+R: Reassessing Java Security API Misuse in Current LLMs: A Replication on JCA and JSSE APIs with External Security Knowledge
Replication finds Java security API misuse persists in current LLMs but is reduced by external knowledge in a model-dependent manner.