Google put out a big blog post on Wednesday about its efforts to clean up ads in terms of malware. The company says bad ads are on the decline thanks to said efforts, which include spending millions of dollars building technical architecture and machine learning models to keep malware away from Google ads before they’re served in the first place.

Here’s a video Google included on how it makes ads better:

The following list is comprised of things Google says it has improved in its detection systems:

• Improved “query watch” for counterfeit ads: While anyone can report counterfeit ads, we’ve widened our proactive monitoring of sensitive keywords and queries related to counterfeit goods which allows us to catch more counterfeit ads before they ever appear on Google
• New “risk model” to detect violations: Our computer scanning depends on detailed risk models to determine whether a particular ad may violate our policies, and we recently upgraded our engineering system with a new “risk model” that is even more precise in detecting advertisers who violate our policies
• Faster manual review process: Some ads need to be reviewed manually. To increase our response time in preventing ads from policy-violating advertisers, we sped up our internal processes and systems for manual reviews, enabling our specialists to be more precise and fast
• Twenty-four hour response time: We aim to respond within 24 hours upon receiving a reliable complaint about an ad to ensure that we’re reviewing ads in a timely fashion

Google says it disabled over 130 million ads last year out of the billions that were submitted. The company says it reduced bad ads by over 50% for the year, compared to 2010.