Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection

J Zhu, S Cai, F Deng, BC Ooi, J Wu - Proceedings of the 32nd ACM …, 2024 - dl.acm.org
Large vision-language models (LVLMs) are markedly proficient in deriving visual
representations guided by natural language. Recent explorations have utilized LVLMs to …

NeurDB: an AI-powered autonomous data system

BC Ooi, S Cai, G Chen, Y Shen, KL Tan, Y Wu… - Science China …, 2024 - Springer
In the wake of rapid advancements in artificial intelligence (AI), we stand on the brink of a
transformative leap in data systems. The imminent fusion of AI and DB (AI× DB) promises a …

Database native model selection: Harnessing deep neural networks in database systems

N **ng, S Cai, G Chen, Z Luo, BC Ooi… - Proceedings of the VLDB …, 2024 - dl.acm.org
The growing demand for advanced analytics beyond statistical aggregation calls for
database systems that support effective model selection of deep neural networks (DNNs) …

Impact of log parsing on deep learning-based anomaly detection

ZA Khan, D Shin, D Bianculli, LC Briand - Empirical Software Engineering, 2024 - Springer
Software systems log massive amounts of data, recording important runtime information.
Such logs are used, for example, for log-based anomaly detection, which aims to …

Impact of log parsing on log-based anomaly detection

ZA Khan, D Shin, D Bianculli, L Briand - arxiv preprint arxiv …, 2023 - orbilu.uni.lu
Software systems log massive amounts of data, recording important runtime information.
Such logs are used, for example, for log-based anomaly detection, which aims to …

Powering in-database dynamic model slicing for structured data analytics

L Zeng, N **ng, S Cai, G Chen, BC Ooi, J Pei… - arxiv preprint arxiv …, 2024 - arxiv.org
Relational database management systems (RDBMS) are widely used for the storage and
retrieval of structured data. To derive insights beyond statistical aggregation, we typically …

Pluto: Sample Selection for Robust Anomaly Detection on Polluted Log Data

L Ma, L Cao, PM VanNostrand, DM Hofmann… - Proceedings of the …, 2024 - dl.acm.org
Log anomaly detection, critical in identifying system failures and preempting security
breaches, finds irregular patterns within large volumes of log data. Modern log anomaly …

Contrastive Learning for Fraud Detection from Noisy Labels

MS Vinay, S Yuan, X Wu - 2024 IEEE 40th International …, 2024 - ieeexplore.ieee.org
Detecting frauds in computing platforms involves identifying malicious user activity sessions.
Recently, deep learning models have been employed to design fraud detection approaches …

PreLog: A Pre-trained Model for Log Analytics

VH Le, H Zhang - Proceedings of the ACM on Management of Data, 2024 - dl.acm.org
Large-scale software-intensive systems often produce a large volume of logs to record
runtime status and events for troubleshooting purposes. The rich information in log data …

LBSC: A Cost-Aware Caching Framework for Cloud Databases

Z Ji, Z **e, Y Wu, M Zhang - 2024 IEEE 40th International …, 2024 - ieeexplore.ieee.org
Caching is a crucial solution to alleviate the high latency and low bandwidth of cloud
databases. However, existing caching algorithms are not suitable for cloud databases as 1) …