Request A Demo
Request A Demo
Menu
Request A Demo

 

Our contextual AI helps you recognize and respond to toxic behaviors harming your online community.

 

Get Started

a6190faf-654c-4aee-a742-51015897abd7
"To build a service that helps inspire people to find and do what they love, we have to deliberately engineer a safe and positive experience. That's why we partner with Spectrum Labs."

 

4239

Rahim Daya
Head of Search

Explore Our AI Model Library

Our models are designed to identify behaviors known to disrupt community building.
✔ Immediately deployable   ✔ Customizable   ✔ Continuously refined

Underage Users

Identifies minors posing as adults.

Sex Solicitation

FOSTA/SESTA-violating attempts to obtain, offer, or negotiate sexual services.

Sexual Harassment

Discerns unwanted sexual advances.

Severe Toxic

Detects violence, threats, and illicit solicitations.

Self-Harm

Detects threats to inflict and/or promote harm on one's own self. 

User Reputation

A custom and configurable system that scores users.

CSAM Grooming

Identifies pedophiles attempting to commit sexual offenses against minors.

Harassment/Cyberbullying

Discerns when someone attempts to intimidate or humiliate another.

Hate Speech

Identifies explicit or suggestive attacks against a person or group based on protected identity classes.

Sexual 

Detects exchanges of a sexual nature.

Doxxing

Identified attempts to obtain and publish private or identifying information about (a particular individual or company) on the Internet, typically with malicious intent.

Phishing/Scams

Attempts to uncover personal financial information or coerce another into giving money.

Offline Transactions/Platform Circumvention 

Identifies attempts to transact off-platform.

Sexual 

Detects exchanges of a sexual nature.

Illegal Solicitation

Recognizes attempts to buy or sell illegal items.  

 

Scams/Spammers

Detects attempts to scam another person.

Insults

Pinpoints rude, aggressive behaviors. 

Severe Threats 

Identifies explicit or implicit intent to harm.

Severe Toxic 

Detects extreme violence, threats, and illicit solicitations. 

Hate Speech

Identifies explicit or suggestive attacks against a person or group based on protected identity classes. 

CSAM Grooming

Identifies pedophiles attempting to commit sexual offenses against minors.

 

Illegal Solicitations

Recognizes attempts to buy or sell illegal drugs or weapons. 

Scams 

Detects attempts to scam another person.

Threats 

Identifies explicit or implicit intent to harm

Harassment/Cyberbullying

Discerns when someone attempts to intimidate or humiliate another. 

Spectrum Labs Initiatives

Throughout the year we examine interesting topics related to Trust & Safety. These explorations help you build a deeper base of knowledge to better serve your communities.

#SaferInternetDay

February 11, 2020 is Safer Internet Day. In support, we invite online communities and platforms of all sizes to commit to returning the Internet to a place of healthy connection by committing at least 1% more of budget spend to Trust & Safety initiatives over the next 12 months.

Learn More     or       View All Initiatives

 
Screen Shot 2020-07-13 at 3.11.22 PM

See how Guardian can work for your community.

Request A Demo

 
shutterstock_1135459364

Spectrum-icon-green

131 Steuart St. Suite 600
San Francisco, CA 94105

(415) 295-2752‬

contact@getspectrum.io

    Stay Informed

    Sign up for our newsletter to receive resources, event invitations and initiative information.
    © Copyright 2020 Spectrum Labs  Privacy Policy   Terms of Use   Legal   GDPR Compliance