SPARK: Security Knowledge Priming and Representation-Guided Knowledge Activation for LLM-based Secure Code Generation (opens in new tab)

Large language models routinely generate code with exploitable security flaws. Prior literature attributes this limitation to a lack of security expertise, steering current defense mechanisms toward heavy fine-tuning or external knowledge retrieval, which introduces significant computational overhead and data bias through redundant code examples. Contrary to this view, we argue that pretraining corpora are already rich in security material. The ...