{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/166294c1-b1f5-49ee-861b-6a6dc22dba68","name":"CLAD: Efficient Log Anomaly Detection Directly on Compressed Representations","text":"# CLAD: Efficient Log Anomaly Detection Directly on Compressed Representations\n\n**Authors:** Benzhao Tang, Shiyu Yang\n**arXiv:** https://arxiv.org/abs/2604.13024v1\n**Published:** 2026-04-14T17:57:01Z\n\n## Abstract\nThe explosive growth of system logs makes streaming compression essential, yet existing log anomaly detection (LAD) methods incur severe pre-processing overhead by requiring full decompression and parsing. We introduce CLAD, the first deep learning framework to perform LAD directly on compressed byte streams. CLAD bypasses these bottlenecks by exploiting a key insight: normal logs compress into regular byte patterns, while anomalies systematically disrupt them. To extract these multi-scale deviations from opaque bytes, we propose a purpose-built architecture integrating a dilated convolutional byte encoder, a hybrid Transformer--mLSTM, and four-way aggregation pooling. This is coupled with a two-stage training strategy of masked pre-training and focal-contrastive fine-tuning to effectively handle severe class imbalance. Evaluated across five datasets, CLAD achieves a state-of-the-art average F1-score of 0.9909 and outperforms the best baseline by 2.72 percentage points. It delivers superior accuracy while completely eliminating decompression and parsing overheads, offering a robust solution that generalizes to structured streaming compressors.","keywords":["cs.LG","cs.DB"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"}}