QuantGuard is a pre-quantization method using differentiable rounding controls, error-guided reversal constraints, output consistency, and weight regularization on a small calibration set to suppress quantization-conditioned backdoors while preserving performance.
Codepurify: Defend backdoor attacks on neural code models via entropy-based purification,
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
Natural backdoors are prevalent in CodeLMs; the authors propose ScanNBT to detect them after analyzing differences from injected backdoors, transferability, and causes.
citing papers explorer
-
Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors
QuantGuard is a pre-quantization method using differentiable rounding controls, error-guided reversal constraints, output consistency, and weight regularization on a small calibration set to suppress quantization-conditioned backdoors while preserving performance.
-
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.