Natural backdoors are prevalent in CodeLMs; the authors propose ScanNBT to detect them after analyzing differences from injected backdoors, transferability, and causes.
Security of language models for code: A systematic literature review,
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
DuCodeMark watermarks code datasets using AST style transformations and repressible poisons for both source-code and decompilation tasks, verified by t-test, with high stealth and a 28.6% performance drop if removed.
citing papers explorer
-
Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models
Natural backdoors are prevalent in CodeLMs; the authors propose ScanNBT to detect them after analyzing differences from injected backdoors, transferability, and causes.
-
DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design
DuCodeMark watermarks code datasets using AST style transformations and repressible poisons for both source-code and decompilation tasks, verified by t-test, with high stealth and a 28.6% performance drop if removed.