Hyphasis screens every input through a mathematical decomposition pipeline. Inputs that cannot decompose are inadmissible by construction. No classifiers. No retraining. No arms race.
The industry defends prompt injection with pattern-matching, regex filters, or secondary LLM classifiers. All three degrade: every novel attack needs an update, every update adds false positives, and every false positive erodes trust. Hyphasis replaces all three with one structural guarantee — input must decompose through a formal pipeline to be admitted. Input that does not map to the operator set has no path through the system. It is not flagged or scored. It is structurally inadmissible.
A stateless HTTP service. Point LLM traffic through the endpoint before it reaches your provider. No SDK, no integration code, no app changes.
A three-stage pipeline parses input into an operator-tagged structure, routes it through component analysis, and maps the result to a formal admissibility space.
Admissible input proceeds to your LLM. Inadmissible input is rejected with a reason code, a quantitative admissibility score, and a causal explanation.
Every verdict is logged with its full decomposition trace, score, and tolerance settings. The Acropolis tier adds a cryptographic proof the pipeline executed correctly.
"Ignore previous instructions" targets the model's control mechanism, not the task. The pipeline has no component for meta-level model control. The input has nowhere to go.
The pipeline verifies seven independent properties of every input. An injection cannot satisfy origin, purpose, or temporal verification. Failure on any one is sufficient for rejection.
Even wrapped in legitimate input, a mixed payload produces a measurable gap on the injection component. Wrapping an injection in context does not eliminate the gap.
For teams deploying LLM endpoints where a prompt injection is not embarrassing — it is a compliance, safety, or security event.
No. It sits between user input and your provider, screening input before it reaches your model. Your LLM, prompts, and application logic are unchanged.
No. The pipeline operates on a proven-complete operator set. Novel attacks don't require updates because novel attacks cannot decompose. There is no classifier to retrain.
Benchmarked against 1,410 cases — legitimate inputs, known injections, novel variants, adversarial payloads. All received the correct verdict: no false negatives, no false positives.
Regex misses novel attacks; secondary classifiers add latency and degrade. Hyphasis runs at parse-time with no model calls and a complete operator set — complete by proof, not by coverage.
Yes — a tolerance parameter per deployment. Tighter rejects more aggressively; looser admits more but logs lower admissibility scores for review.
Hyphasis is available for design-partner access. The live endpoint is operational at api.metacortexdynamics.com:8443.
Design-partner access is open. The endpoint is live.