SoylentNews is people
SoylentNews
Submission Preview
De-anonymizing programmers from executable binaries
We are able to de-anonymize executable binaries of 20 programmers with 96% correct classification accuracy. In the de-anonymization process, the machine learning classifier trains on 8 executable binaries for each programmer to generate numeric representations of their coding styles.
and
For the first time in programmer de-anonymization, we show that we can still identify programmers of optimized executable binaries. While we can de-anonymize 100 programmers from unoptimized executable binaries with 78% accuracy, we can de-anonymize them from optimized executable binaries with 64% accuracy.
What are the real-world implications of this? It doesn't sound like it would be accurate enough yet to be useful for "programmer tracking" as such, but perhaps the research could be of some heuristical significance for detecting new forms of malware?
