Description:

Letter Salad or Salad for short, is an efficient and flexible implementation of the well-known anomaly detection method Anagram by Wang et al. (RAID 2006) and provides various extensions to it.

Salad is based on n-gram models, that is, data is represented as all its substrings of length n. During training these n-grams are stored in a Bloom filter. This enables the detector to represent a large number of n-grams in little memory and still being able to efficiently access the data. Salad extends Anagram by allowing various n-gram types, a 2-class version of the detector for classification and various model analysis modes.

Changes to previous version:

A teeny tiny fix to correctly handle input strings shorter than a registers width

BibTeX Entry: Download

Corresponding Paper BibTeX Entry: Download

Supported Operating Systems: Linux, Windows, Unix, Posix, Mac Os X

Data Formats: Binary, Txt

Tags: Sequence Analysis, Sparse Learning

Archive: download here

Other available revisons

Version	Changelog	Date
0.6.1	A teeny tiny fix to correctly handle input strings shorter than a registers width	June 17, 2016, 11:26:34
0.6.0	After a full year of development we proudly present you several new features, plenty of bug fixes and better performance :) It now is possible to process data on bit granularity salad [train|inspect] --binary Performance improvements while simultaneously preserving and further advancing readability of the source code. Suppress the verbose output of Salad salad [train|predict] -q Extend the (unit) testing framework to support test of the overall application and memchecks using valgrind. Testing mode was renamed: salad dbg -> salad test Allow to select either client or server-side data when processing network communication. libfoodstoragebox A library encapsulating advanced data structures such as bloom filters. Fixes for a critical bug when using group input and several minor issues. An optionally compressed, text-based model file format salad train -F (txt|archive) The default hashset ('simple2') makes use of djb2 hash Flawless builds using gcc, mingw and clang	December 1, 2015, 16:17:35
0.5.0	Lots and lots of cool new features and bugfixes ;) Refinements to the user interface: This includes a progress indicator, colors, etc. Determine the expected error (salad-inspect) Enable the user to echo the used parametrization: salad [train|predict|inspect] --echo-params Allow to set the input batch size as program argument: salad [train|predict|inspect] --batch-size libsalad: The library allows to access salad's basic functions Installers and precompiled binaries: Windows installer, Debian (ppa:chwress/salad) & RPM packages as well a generic linux installers. Various minor bug fixes Support for "length at end" zip files Improve salad's usage in a 2-class setting: salad [train|predict|inspect] --input-filter	August 22, 2014, 17:54:56
0.4.3	Fixes a bug in prediction mode for the use of archives when -DUSE_NETWORK=ON	August 11, 2014, 11:16:49
0.4.2	Fixes a bug in the unit testing framework on Windows	December 25, 2013, 08:00:12
0.4.1	Fixes a critical bug that rendered the 0.4.0 release pretty much unusable	December 17, 2013, 16:05:06
0.4.0	Support for processing network dumps and capturing packets and streams directly from network interfaces. Furthermore we integrated unit tests, established a logging infrastructure for more consistent output and fixed various bugs.	November 28, 2013, 16:13:40
0.3.5	Initial Announcement on mloss.org.	October 15, 2013, 11:00:26

Comments

No one has posted any comments yet. Perhaps you'd like to be the first?

Leave a comment

You must be logged in to post comments.