A test-driven pipeline with an auto-constructed privacy feature library detects 2.56 times more confirmed privacy leaks in LLM-based code generation than existing baselines.
arXiv preprint arXiv:2412.18573 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Fine-tuning and prompting reduce some CWEs in AI-generated code but frequently introduce new weaknesses, with no strategy working reliably across models or languages.
citing papers explorer
-
Probing Privacy Leaks in LLM-based Code Generation via Test Generation
A test-driven pipeline with an auto-constructed privacy feature library detects 2.56 times more confirmed privacy leaks in LLM-based code generation than existing baselines.
-
On Fixing Insecure AI-Generated Code through Model Fine-Tuning and Prompting Strategies
Fine-tuning and prompting reduce some CWEs in AI-generated code but frequently introduce new weaknesses, with no strategy working reliably across models or languages.