Classification of Software Behaviors for Failure Detection: A Discriminative Pattern Mining Approach

Software is a ubiquitous component of our daily life. We of- ten depend on the correct working of software systems. Due to the di±culty and complexity of software systems, bugs and anomalies are prevalent. Bugs have caused billions of dollars loss, in addition to privacy and security threats. In this work, we address software reliability issues by proposing a novel method to classify software behaviors based on past history or runs. With the technique, it is possible to gener- alize past known errors and mistakes to capture failures and anomalies. Our technique ¯rst mines a set of discriminative features capturing repetitive series of events from program execution traces. It then performs feature selection to select the best features for classi¯cation. These features are then used to train a classi¯er to detect failures. Experiments and case studies on traces of several benchmark software systems and a real-life concurrency bug from MySQL server show the utility of the technique in capturing failures and anomalies. On average, our pattern-based classi¯cation technique out- performs the baseline approach by 24.68% in accuracy1.
Date: August 30, 2009
Book Title: Proc. 2009 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD'09)
Type: InProceedings
Address: Paris, France
Downloads: 515

Has 1 soft copy


remote link

Bibtex


@InProceedings{Classification_of_Software_Behaviors_for,
  author = "David Lo and Hong Cheng and Jiawei Han and Siau-Cheng Khoo and ChengNian Sun",
  title = "{Classification of Software Behaviors for Failure Detection: A Discriminative Pattern Mining Approach}",
  month = "August",
  year = "2009",
  address = ", Paris, France",
  booktitle = "Proc. 2009 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD'09)",
}