DeepGuard aggregates multi-layer representations in code LLMs to raise the secure-and-correct generation rate by 11.9% on average over baselines like SVEN while preserving correctness and generalizing to new vulnerability types.
Thomas Dohmke
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
A pipeline architecture using XML extraction, structural normalization, and constrained LLM generation to translate Rockwell ladder logic to Siemens S7 programs with reported high semantic consistency.
citing papers explorer
-
DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation
DeepGuard aggregates multi-layer representations in code LLMs to raise the secure-and-correct generation rate by 11.9% on average over baselines like SVEN while preserving correctness and generalizing to new vulnerability types.
-
Ladder Logic Translation using Large Language Models in Industrial Automation
A pipeline architecture using XML extraction, structural normalization, and constrained LLM generation to translate Rockwell ladder logic to Siemens S7 programs with reported high semantic consistency.