@inproceedings{71f7606ff7664ba0b535f475b77c8b37,
title = "Trade-offs in automatic provenance capture",
abstract = "Automatic provenance capture from arbitrary applications is a challenging problem. Different approaches to tackle this problem have evolved, most notably a. system-event trace analysis, b. compile-time static instrumentation, and c. taint flow analysis using dynamic binary instrumentation. Each of these approaches offers different trade-offs in terms of the granularity of captured provenance, integration requirements, and runtime overhead. While these aspects have been discussed separately, a systematic and detailed study, quantifying and elucidating them, is still lacking. To fill this gap, we begin to explore these trade-offs for representative examples of these approaches for automatic provenance capture by means of evaluation and measurement. We base our evaluation on UnixBench{\textemdash}a widely used benchmark suite within systems research. We believe this approach will make our results easier to compare with future studies.",
keywords = "LLVM, Provenance, SPADE, Strace, Taint tracking",
author = "Manolis Stamatogiannakis and Hasanat Kazmi and Hashim Sharif and Remco Vermeulen and Ashish Gehani and Herbert Bos and Paul Groth",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; 6th International Provenance and Annotation Workshop, IPAW 2016 ; Conference date: 07-06-2016 Through 08-06-2016",
year = "2016",
doi = "10.1007/978-3-319-40593-3\_3",
language = "Ingl{\'e}s",
isbn = "9783319405926",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "29--41",
editor = "Boris Glavic and Marta Mattoso",
booktitle = "Provenance and Annotation of Data and Processes - 6th International Provenance and Annotation Workshop, IPAW 2016, Proceedings",
}