Google Maps details how it combatted scamming in 2022

Abner Li | Mar 31 2023 - 8:00 am PT

Reviews, pictures, and other user-generated content play a big role in Google Maps. Google today detailed how it combated fake contributions to Maps in 2022.

Last year, Google Maps “launched a significant update” that allows its machine learning models to “identify novel abuse trends many times faster than previous years.”

For example, our automated systems detected a sudden uptick in Business Profiles with websites that ended in .design or .top — something that would be difficult to spot manually across millions of profiles. Our team of analysts quickly confirmed that these websites were fake – and we were able to remove them and disable the associated accounts quickly.

To combat scammers uploading images overlaid with inaccurate phone numbers “hoping to trick unsuspecting victims into calling the fraudster instead of the actual business,” a new ML model can recognize pictures with numeral overlays “by analyzing specific visual details and the layouts of photos.”

With this model, we successfully detected and blocked the vast majority of these fraudulent and policy-violating images before they were published.

In all, Google Maps removed “over 200 million photos and 7 million videos that were blurry, low quality, or violated our content policies” in 2022. Additionally, 115 million policy-violating reviews were removed, for a 20% increase compared to 2021. Google says the “vast majority” of these fraudulent reviews were caught before they were seen.

As bad actors continue to evolve their strategies, we stopped 20 million attempts to create fake Business Profiles, which is 8 million more than in 2021. We also put protections in place for 185,000 businesses after detecting suspicious activity and abuse attempts.