Tensor Trust
A benchmark dataset for evaluating prompt injection defense capability, containing adversarial prompts and defense tasks.
Timeline (last 90 days)
The audit benchmark covers NLI (e-SNLI), adversarial syntactic shortcuts (HANS), synthetic clinical triage (N=900), prompt injection defense (Tensor Trust, N=250), and an 86-case logic-gate trigger suite.
In the prompt-injection defense task (N=250), System 1 models with 4B parameters or more achieve an AUROC of 0.988 to 0.998, a recall of up to 95.2%, and a 0.0% false positive rate at 48 to 60 milliseconds of latency.
All Facts (2)
The audit benchmark covers NLI (e-SNLI), adversarial syntactic shortcuts (HANS), synthetic clinical triage (N=900), prompt injection defense (Tensor Trust, N=250), and an 86-case logic-gate trigger suite.
50%UnverifiedIn the prompt-injection defense task (N=250), System 1 models with 4B parameters or more achieve an AUROC of 0.988 to 0.998, a recall of up to 95.2%, and a 0.0% false positive rate at 48 to 60 milliseconds of latency.
50%