Cybersecurity · AWS
Abnormal Security
Abnormal runs a cloud-native, API-first behavioral AI platform that integrates with cloud email and collaboration suites (e.g., Microsoft 365, Google Workspace) outside the mail flow, ingesting user, email, and identity telemetry into proprietary behavioral models and a data lake to drive detection, response, and human-risk scoring.[1][5][7][8][9] Its core is a proprietary behavioral foundation model and related ML pipelines hosted in its own cloud environment, exposed through its SaaS console and APIs rather than via public/open-source model distribution.[7][9]
Foundation proximity: Native (own / self-hosted weights)
Foundational models & how they consume them
PrimaryAbnormal Behavioral Foundation Model· Abnormal (self-hosted) · Native (own / self-hosted weights)
SecondaryAbnormal ABX / behavioral ML models· Abnormal (self-hosted) · Native (own / self-hosted weights)
Cloud & datastore
AWSPostgreSQLAmazon S3 (data lake/object storage)Elasticsearch/OpenSearch (log/search, inferred)Compliance
SOC 2 (inferred from enterprise email security norm)ISO 27001 (inferred)GDPR-aligned data processing (inferred)Similar companies
DarktracePalo Alto NetworksSentinelOneSnykCrowdStrikeOktaOthers that build on proprietary / self-built models
AbridgeAdobeAI21 LabsAleph AlphaAmbienceAndurilExplore
FAQ
Does Abnormal Security use a foundational AI model?
Abnormal Security uses Abnormal Behavioral Foundation Model, Abnormal ABX / behavioral ML models (Native (own / self-hosted weights)).
What cloud does Abnormal Security run on?
Abnormal Security runs on AWS.
What database does Abnormal Security use?
Abnormal Security uses PostgreSQL, Amazon S3 (data lake/object storage), Elasticsearch/OpenSearch (log/search, inferred).
How close does Abnormal Security run to the foundational model?
Abnormal Security is Native (own / self-hosted weights) — close to the metal, so cheaper tokens and more control over outputs.
Sources
abnormalsecurity.com ↗Also on the map
← Full orbit map (260 companies) · Score your own stack →
Architecture inferred from public sources · confidence low · verify before betting on a detail.