Core - Content Review Engine
by T3K.AI
About CORE – Content Review Engine
Screening digital data at scale for illegal and inappropriate content
API-level access to T3K’s machine learning technology provides the ability to detect contents in data at scale, identifying bad actors in online networks, through hosted data, or through seized evidence.
Users can perform quick and complete scans of the data CORE is directed at:
- Running on internal or external online networks.
- Scanning millions of media contents per day.
- Detecting new and self-produced content not found in hash databases.
- Extremely low false positive ratio.
- Integrates into third party tools or directly into networks, and scales easily according yo data volume.
- Used globally by leading law enforcement authorities for detection of CSAM (child sexual abuse material), TVEC (terrorist and violent extremist content), financial crime, and more.
CORE features
CORE’S screening capabilities accelerate investigations which involve large amounts of seized digital devices. The models are constantly evolving and are currently generating matches on the following recognition classes:
- Child sexual abuse material (CSAM),incl. facial, age, and gender estimation.
- Identity cards: passports and cards potentially displaying an identity
- Car license plates
- Additional classes can be trained upon customer request.
- Military equipment: guns, military uniforms, armored vehicles.
- Screenshots, handwriting documents and maps.
- Terrorist and violent extremist content (TVEC): masked individuals, ISIS flags and different logos of propaganda media outlets.
CORE provides face recognition from uploaded reference images.
CORE detects key elements of visual 2D patterns to recognize logos, art, bank notes, tattoos, tapestry, etc. from uploaded reference images.
CORE can be enabled to search for pictures by describing them with natural language (text2image), or by similarity searching with reference images (image2image)
T3K delivers Al-enabled solutions to screen, analyze and detect contents in digital data.
CORE (Content Review Engine) allows screening of hosted digital media data for the presence of CSAM (child sexual abuse material), TVEC (terrorist and violent extremist content) and other illicit images, videos or documents. CORE can be integrated into existing networks, as well as digital forensic, eDiscovery and other review platforms using a versatile API.
Sophisticated media classification and content detection build the foundation of a successful investigation involving large amounts of digital data. Additionally to utilizing Al classifiers, CORE offers pattern recognition, image-to-image similarity search and text-to-image search. Adding our extremism desk database makes CORE the most powerful counter-terrorism solution.
All software developed by T3K is fully containerized, allowing for easy adoptions into the most common cloud and edge environments (AWS, Azure, …). Due to the modular containerized setup, our solutions in the cloud can be scaled horizontally and vertically.
- Seamless integration into existing backend infrastructure or existing platform, like Nuix.
- Media objects are directed to the CORE server during or after processing in the existing platform, automatically classified based on the chosen Al classifiers, and tagged for review in the integrating platform’s frontend.
- Media data is also “indexed”, allowing real-time search using natural language keywords.
- Optional: offering a GUI that lets the user “cluster” images automatically, according to their similarity with each other.
Did you miss our T3K webinar? In this 45 minute overview, discover T3K Core’s screening capabilities, and how it’s being used to accelerate investigations which involve large amounts of seized digital devices. Core’s constantly evolving recognition classes include: CSAM, TVEC, Identity Cards, Military Equipment, and much more.
