HUMAN retweetledi
Otherwise competent engineering teams fail at bot detection because they model the problem as anomaly detection. They think they can make a model of normal human use and then use ML to find the outliers. This dramatically underestimates the adversary.
We crushed this problem at @SecureWithHUMAN by completely different means: active, dynamic side channel analysis.
That's why our capabilities are *additive* for customers like Google and Microsoft, who have world class AI teams themselves. HUMAN adds extraordinary side channel analysis capabilities that are otherwise unseen outside of nation state cyberwarfare. That's why HUMAN has triggered more takedowns and more arrests than any other botnet defender.
No one's getting convicted on some AI model's anomaly detection. AI fraud detection models never *stop* the predators, only delay them. The adversaries adapt, infect new computers, steal more real accounts and identities, and keep going once they hide in the noise again. HUMAN nails proof to the wall. It's the serious choice for everyone who wants to deal consequences to the adversary.
Nikita Bier@nikitabier
People come X to get a pulse on humanity. Because of that, the platform must make every effort to resist anything that misrepresents or adulterates that pulse. There is nothing more unsettling than expecting you’re reading the words of a human -- only to find it was a machine, or an account operating at the direction of an undisclosed commercial or governmental entity. In the AI era, our product, policies, and approach will need to evolve meaningfully. Some things may not work, but we intend to employ every available tool and strategy to secure the global town square.
English
