Get the latest tech news

Bears, mice, and moles aren't enough: a better approach for preventing fraud


Traditional fraud defenses struggle to keep up with modern threats like residential botnets and AI-powered automation. This article introduces Stytch’s practical framework for evaluating and improving fraud prevention, with a focus on better signal gathering, smarter decisioning, and resilient enforcement.

In the last year, we’ve observed increasing fraud activity, from low-effort automated spam (made easier by LLMs, unfortunately) to sophisticated account takeover attacks from residential botnets. It may seem obvious to break down the fraud prevention process in this way - it’s very similar to John Boyd’s OODA loop concept - but it gives us a common language and separation of concerns. For example, credential stuffing attacks almost always have a high rate of attempts to login to accounts that don’t exist at all - that’s data known to the authentication system, but it doesn’t show up at all in the attributes that Device Fingerprinting measures.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of fraud

fraud

Photo of mice

mice

Photo of bears

bears

Related news:

News photo

Trump guts digital ID rules, claims they help 'illegal aliens' commit fraud

News photo

Girls Do Porn Ringleader Pleads Guilty, Faces Life In Prison | Michael Pratt led Girls Do Porn, a sex trafficking operation that targeted hundreds of young women with force, fraud and coercion.

News photo

A Big, Pending Case Unites and Divides the Music Industry Over Fraud in Streaming