Plagiarism is a problem with far-reaching consequences for the sciences. However even today's
best software-based systems can only reliably identify copy & paste plagiarism. Disguised
plagiarism forms including paraphrased text cross-language plagiarism as well as structural
and idea plagiarism often remain undetected. This weakness of current systems results in a
large percentage of scientific plagiarism going undetected. Bela Gipp provides an overview of
the state-of-the art in plagiarism detection and an analysis of why these approaches fail to
detect disguised plagiarism forms. The author proposes Citation-based Plagiarism Detection to
address this shortcoming. Unlike character-based approaches this approach does not rely on
text comparisons alone but analyzes citation patterns within documents to form a
language-independent semantic fingerprint for similarity assessment. The practicability of
Citation-based Plagiarism Detection was proven by its capability to identify so-far non-machine
detectable plagiarism in scientific publications.