> ## Documentation Index
> Fetch the complete documentation index at: https://docs.deepblocker.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# The "detector caught" column

> What Caught, Missed and Not scored mean, where the 80% threshold comes from, and why the detector's result sits next to each person's result.

Every test call is also a test of DeepBlocker's deepfake detector. After the call, the detector scores the attacker's voice on the recording and says whether it would have flagged it. The results page puts that verdict next to the person's verdict, on the same call.

The console explains the column like this: "**Detector caught**: your blue-team deepfake detector flagged the synthetic voice, out of the calls it scored. Higher is better. 'Not scored' means the detector has not finished analysing yet (it scores shortly after the call)."

## The three states

| Badge | Meaning | How it is decided |
| - | - | - |
| **Caught** | The detector would have flagged the cloned voice before a person was fooled | The fake score reached the threshold |
| **Missed** | The detector would not have flagged it | The fake score stayed under the threshold |
| **Not scored** | No usable score exists yet | The recording was not ready, scoring failed, or the call has no usable recording |

Hover a badge for the detail: **Scored X% fake (threshold Y%)**, and the model name when known. A failed scoring shows **Scoring failed** with the reason.

## The threshold

The threshold is 80% unless the detector reports another for that call. A call scoring 80% fake or more is **Caught**. The hover text always shows the threshold that was applied, so a verdict can be checked.

## Where it appears

| Place | What you see |
| - | - |
| The **Detector** column of the results table | One badge per person, with the background sound used on the call. See [Read your results](https://docs.deepblocker.ai/vishing/results/overview.md) |
| **Attack and defence on the same calls** | **Calls our detector would have blocked**, with the number scored in brackets, and **Residual: failed and not blocked** |
| The breakdown tables by level, tactic and warm-up | A **Detector caught** column: the catch rate out of the calls scored |
| Help desk and call-back results | A **Detector verdict** or **Detector on caller** column. See [Help desk and call-back results](https://docs.deepblocker.ai/vishing/results/variants.md) |
| The call detail window | The score and the model. See [One call in detail](https://docs.deepblocker.ai/vishing/results/call-detail.md) |
| The result webhook | A `defenseVerdict` block. See [Send results to your SIEM or LMS](https://docs.deepblocker.ai/vishing/results/webhook.md) |

## Why it matters

The worst case is a person who failed on a call the detector also missed. The results page calls this **Got through**, or **Residual**. You want it at 0. A high catch rate on the calls your people fell for means a real attack with that voice would have been stopped before anyone picked up.

> [!NOTE]
>
> On a call-back trap the caller is a real member of staff, not the AI. There the detector scores a real voice, and a real employee should **not** be flagged. A **Caught** on that view is a false alarm worth telling us about.

## Problems

> [accordion] Every call says Not scored
>
> The detector scores a call shortly after it ends. Wait a few minutes, then click **Sync & analyze** on the results card. A call with no usable recording stays **Not scored**.

> [accordion] The catch rate changed after I first looked
>
> Verdicts land as recordings are scored. The percentages are worked out over the calls scored so far, so they settle once every call has a verdict.

> [accordion] The hover shows a different threshold from 80%
>
> The detector reported its own threshold for that call. The verdict uses the threshold shown.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.