Douglas-Quaid is an open-source image matching library that combines fuzzy hashes and ORB with decision fusion and self-calibration, reporting 80% accuracy on a CERT screenshot dataset.
Open Dataset of Phishing and Tor Hidden Services Screen-captures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Security analysts need to classify, search and correlate numerous images. Automatic classification tools improve the efficiency of such tasks. However, the main resources to develop these tools are datasets, which are introduced and provided by the present paper, for the specific cases of visual correlation of phishing and onion websites. CIRCL's Open-Source tools are the sources of these screenshots, which had been manually verified against personal information leaks. Usage examples of these datasets are proposed in the current paper. These researches directions are, however, not the main contribution of the paper. The main contribution is the availability of the two datasets.
fields
cs.CR 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Douglas-Quaid -- Open Source Image Matching Library
Douglas-Quaid is an open-source image matching library that combines fuzzy hashes and ORB with decision fusion and self-calibration, reporting 80% accuracy on a CERT screenshot dataset.