Map / Model Security / LatticaAI

LatticaAI

Israel · Founded 2024 · Raised $3.25M

Quick answer: LatticaAI is an AI security company based in Israel and founded in 2024, working in Model Security and AI Data Governance. It has raised $3.25M from investors including Cyber Fund, Lightshift Capital and Sentient.

Model SecurityAI Data Governance

Capabilities

Privacy-preserving AI inference platform using Fully Homomorphic Encryption; encrypted model inputs and outputs across browser, mobile, and server contexts; integration with major LLM providers; FHE-optimized for AI/ML workloads; privacy-preserving alternative to plaintext model APIs.

Sensors / integration

Client-side encryption SDK; FHE-based inference layer; integration with browser, mobile, and server runtimes; partnerships with infrastructure providers.

Protections

Cryptographic guarantee that model inputs remain private from the model provider; encrypted inference preserving model utility; protection of sensitive prompts and responses; supports regulated workloads requiring zero plaintext exposure to AI providers.

Differentiator

FHE-specialized AI inference platform; positioning alongside Mirror Security, Protopia, and Confident Security in the cryptographic-AI-privacy category; differentiated by browser-level deployment options.

Team & funding

Founders
Rotem Tzabari
Total raised
$3.25M
Investors
Cyber Fund, Lightshift Capital, Sentient, XT Venture Capital, Sandeep Nailwal

Other Model Security companies

ActiveFence · Advai · Adversa AI · AI Aramid · Alice · AptaSentry · Arize AI · Attestable · Bosch AIShield · Citadel AI · Cranium AI · DataKrypto · See all →

Last updated · Get the “Listed on” badge