Proof, not promises.

Check every number. Download every dataset.

0

false positives on 10,014 legitimate prompts

0

data leak attempts blocked

0

attack prompts tested

0

independent attack datasets

100% deterministic — no ML, no drift

Datasets

Every prompt is sourced from a public, independently-maintained dataset. Nothing is synthetic. Nothing is cherry-picked.

NVIDIA Garak v0.14.0

Attack

NVIDIA open source

4,592 prompts

JailbreakBench

Attack

Academic — OWASP LLM Top 10

199 prompts

StrongREJECT

Attack

AlignmentResearch

313 prompts

allenai/WildJailbreak

Attack

Allen Institute for AI — MIT licence

82,975 prompts

Stanford Alpaca

Known-good

Stanford University

4,998 prompts

Databricks Dolly

Known-good

Databricks

5,016 prompts

Independent comparison

We ran 9,000 prompts through both Thorn Layer and Lakera Guard under identical conditions. Here are the results.

0

Thorn Layer false positives

on 388 legitimate prompts

4

Lakera Guard false positives

on 388 legitimate prompts (1.03%)

False positives (388 real prompts)

Thorn Layer

0

Lakera Guard

4 (1.03%)

Data leak prevention (target pattern)

Thorn Layer

100%

Lakera Guard

42%

Real-world latency

Thorn Layer

10–30ms

Lakera Guard

77ms+

New threat response

Thorn Layer

Seconds

Lakera Guard

24 hours

Deterministic

Thorn Layer

Lakera Guard

Published methodology

Thorn Layer

Lakera Guard

No tuning required

Thorn Layer

Lakera Guard

Indie/SMB pricing

Thorn Layer

Lakera Guard

Lakera tested using Prompt Defense Only policy on a 9,000-prompt stratified sample. Thorn Layer uses a deterministic engine — same input, same output, every time. Full dataset breakdown on this page. Lakera latency measured from EU VPS — real-world latency varies by region.

Every number on this page is real. Read the full methodology or start free.

Lakera Guard is a trademark of Lakera AI. Comparison based on independent testing, April 2026.

Methodology

Thorn Layer uses a deterministic engine. Same input, same output, every time. No ML, no drift, no false positives.

In December 2025, the UK National Cyber Security Centre stated that prompt injection may never be fully solved at the model level. Read the NCSC guidance.

Protect your LLM application

One line of code. Always protected.