Online scams across email, short message services, and social media increasingly challenge everyday risk assessment, particularly as generative AI enables more fluent and context-aware deception. Although transformer-based detectors achieve strong predictive performance, their explanations are often opaque to non-experts or misaligned with model decisions. We propose VEXA, an evidence-grounded and persona-adaptive framework for generating learner-facing scam explanations by integrating GradientSHAP-based attribution with theory-informed vulnerability personas. Evaluation across multi-channel datasets shows that grounding explanations in detector-derived evidence improves semantic reliability without increasing linguistic complexity, while persona conditioning introduces interpretable stylistic variation without disrupting evidential alignment. These results reveal a key design insight: evidential grounding governs semantic correctness, whereas persona-based adaptation operates at the level of presentation under constraints of faithfulness. Together, VEXA demonstrates the feasibility of persona-adaptive, evidence-grounded explanations and provides design guidance for trustworthy, learner-facing security explanations in non-formal contexts.

翻译：电子邮件、短消息服务和社交媒体中的在线诈骗日益挑战日常风险评估，尤其是生成式人工智能能够实现更流畅、更具情境感知的欺骗行为。尽管基于Transformer的检测器实现了强大的预测性能，但其解释对非专业人士往往不透明或与模型决策不一致。我们提出VEXA，一个基于证据与角色自适应的框架，通过将基于GradientSHAP的归因方法与理论驱动的脆弱性角色模型相结合，生成面向学习者的诈骗解释。跨多通道数据集的评估表明，将解释锚定于检测器衍生的证据可在不增加语言复杂度的前提下提升语义可靠性，而角色条件调节则能在不破坏证据对齐的前提下引入可解释的风格变化。这些结果揭示了一个关键设计洞见：证据锚定主导语义正确性，而基于角色的自适应在忠实性约束下作用于呈现层面。VEXA共同证明了角色自适应、证据锚定式解释的可行性，并为非正式场景下面向学习者的可信安全解释提供了设计指导。