SOURCE: Smyte

April 25, 2017 06:00 ET

Smyte Releases New Anti-Spam and Fraud/Harassment Prevention Tools

The online security company's trust and safety platform now includes a custom rules engine and deep learning neural network models for supervised and unsupervised image classification

SAN FRANCISCO, CA--(Marketwired - Apr 25, 2017) -  Smyte has enhanced its SaaS trust and safety platform with new tools for stopping the latest online spam, fraud and harassment scams. Smyte's service, used by leading social networks and peer-to-peer marketplaces, analyzes over five billion online actions every month using a variety of techniques. The updated Smyte service now includes deep learning neural networks and a customizable rules engine, making it harder for Internet mischief-makers to disrupt online businesses.

The current generation of online spammers and fraudsters are benefitting from several technical and human developments. For example: IP addresses are cheaper due to vulnerable IoT devices and cracked Android phones; attackers can easily share their code via GitHub and criminal marketplaces; consumers are getting smarter about privacy, which means companies can't rely on VPN/Tor being a reliable signal of an illegitimate user; the price of CAPTCHA solving services and burner phone numbers continues to drop, which means SMS verification and CAPTCHAs aren't as effective; more people are coming online, resulting in more attackers and more unique ways to monetize the attacks within new geographies.

Social networks and peer-to-peer marketplaces are particularly vulnerable to the new wave of Internet attacks -- but so, too, are SaaS providers, financial services organizations, healthcare companies and large enterprises in general. Smyte's trust and safety platform is unique among online security products in that it's constantly monitoring, aggregating, learning and adapting to new scams and harassment methods as it gathers information.

To combat the latest online schemes, Smyte's service now uses deep neural networks -- software programs that are influenced by how the brain's neocortex interprets images -- among its ensemble of techniques. For instance, Smyte created a perceptual hash using deep learning that is resilient to advanced attacks like cropping, rotating, re-texturing and watermarking. This replaces previous perceptual hashing techniques, like difference hashing, that are easily defeated through automation.

Smyte also uses deep neural networks for supervised (known images like porn, violence, copyrighted material, etc.) and unsupervised (anomalies, i.e. something "different looking") image classification. One way to ruin a user's online experience is for them to be exposed to extreme gore and violent imagery. Smyte has developed a deep neural network classifier for images that can identify extremely violent content, and stop them from being sent to users. In terms of unsupervised image detection, Smyte uses a deep neural network model to group similar looking images together. By looking at how quickly a "cluster" of similar images is growing (i.e. if a lot of users are uploading images that look similar), Smyte can identify spam campaigns without any user reporting.

The enhanced Smyte service now also includes a powerful feature extraction and rules language. The Smyte Query and Rule Language (SQRL) helps companies prevent fraud by allowing users to create their own rules. For example, a company might create a rule that says, "Block any duplicate message that was sent to at least three people and is in the top 1% of messages sent on Smyte's service by volume," or "Block any login coming from a country and device we have never seen this user use before."

The rules are stateful and can incorporate streaming data aggregations, such as rate limiting, streaming counts, time windowed set cardinalities, nearest neighbor search and streaming quantile analysis. Facebook and Google have built similar engines for stopping spam, fraud and harassment, but they are not available to the general public and are designed for highly technical engineers, not analysts.

"As we've said before: what worked in scam and spam prevention yesterday might not work today or tomorrow. Companies need to be up on the latest attacks, and they need security systems that evolve and mature as the nature of attacks change," says Pete Hunt, Co-founder and CEO at Smyte. "What we've done in this latest release is attempt to automate our customers' defenses through deep learning, thus decreasing the burden on internal teams, while also giving Smyte users more control to prevent the attacks that are affecting them most. We've had great feedback from our users so far, and we are excited to be at the forefront of the next generation of spam, fraud and online harassment prevention."

About Smyte
Smyte is an online security startup based in San Francisco, California. The company was founded in 2014 by former Facebook, Google and Instagram security and infrastructure engineers. Its trust and safety platform is used by many of the leading P2P marketplaces and social apps to combat spam, scam, online harassment and credit card fraud. Smyte is a graduate of the Y Combinator Winter 2015 program. More info at www.smyte.com.

Contact Information