Dartmouth and UC Berkeley researchers have developed new software to
detect faked photos, using a geometric algorithm to locate inconsistent shadows that are not obvious to the naked eye.
Not exact matches
A «generator» attempts to produce artificial outputs (like images) that resemble real examples (actual
photos), while a «discriminator» tries to
detect real from
fake.
Attempts to
detect scammers typically look at the characteristics which follow from these two requirements — for example using a
fake photo, accessing the site from a country other than their stated location, or sending contact details in messages.