通过不确定性感知对比学习，提升恶意内容检测的准确率与鲁棒性
Learning Robust Representations for Malicious Content Detection via Contrastive Sampling and Uncertainty Estimation
- 基于样本置信度动态调整对比损失权重，增强模型对噪声的适应能力
- 在恶意内容分类中实现超93.38%准确率、近满分召回率和高精度
- 适合高风险场景如网络安全、生物医学文本分析中的弱监督学习
我们提出不确定性对比框架（UCF），一种融合不确定性感知对比损失、自适应温度缩放和自注意力引导LSTM编码器的正例-未标记例（PU）表示学习框架，以在噪声大且数据不平衡条件下提升分类性能。UCF根据样本置信度动态调整对比权重，利用正例锚点稳定训练过程，并针对批处理级差异自适应调节温度参数。应用于恶意内容分类时，UCF生成的嵌入使多种传统分类器达到超过93.38%的准确率、精度高于0.93、接近完美的召回率，同时极少出现误报，且具备优异的ROC-AUC表现。可视化分析显示正例与未标记样本间存在清晰分离，验证了该框架生成校准良好、判别性强的嵌入能力。这些结果表明UCF是网络安全和生物医学文本挖掘等高风险领域中一种鲁棒且可扩展的PU学习方案。
原文摘要 · Abstract (English)
We propose the Uncertainty Contrastive Framework (UCF), a Positive-Unlabeled (PU) representation learning framework that integrates uncertainty-aware contrastive loss, adaptive temperature scaling, and a self-attention-guided LSTM encoder to improve classification under noisy and imbalanced conditions. UCF dynamically adjusts contrastive weighting based on sample confidence, stabilizes training using positive anchors, and adapts temperature parameters to batch-level variability. Applied to malicious content classification, UCF-generated embeddings enable multiple traditional classifiers to achieve more than 93.38% accuracy, precision above 0.93, and near-perfect recall, with minimal false negatives and competitive ROC-AUC scores. Visual analyses confirm clear separation between positive and unlabeled instances, highlighting the framework's ability to produce calibrated, discriminative embeddings. These results position UCF as a robust and scalable solution for PU learning in high-stakes domains such as cybersecurity and biomedical text mining.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。