Q1. [4] § Test Yourself § Assertion and reasoning-based questions § Case study-based questions
PQR Security Solutions has designed an AI Model to detect cyber attacks on E-Commerce websites. For this, various network activities were monitored and analyzed on one of the websites. The model was tested on a dataset of 1500 network activities. Out of these, the model correctly predicted that 1000 were cyber attacks. It also correctly identified that 250 were not cyber attacks. However, the model predicted that 200 were cyber attacks but actually they were not. Additionally, it predicted that 50 were not cyber attacks but they actually were.
Read the following paragraph and answer the questions that follow:
- (A) Draw the confusion matrix based on the given scenario. [2]
- (B) How many total cases are True Negative in the above scenario ? [1]
- (C) Calculate Precision. [1]
Previously asked in CBSE board exam
2026 104 Q19
Generated by claude-sonnet-4-6 · 2026-06-21 03:19 · grounding stimulus
Model Answer
(A) Confusion Matrix:
| | Predicted: Attack | Predicted: Not Attack |
|---|---|---|
| Actual: Attack | 1000 (TP) | 50 (FN) |
| Actual: Not Attack | 200 (FP) | 250 (TN) |
(B) True Negative (TN):
True Negative = cases correctly identified as not cyber attacks = 250
(C) Precision:
$$\text{Precision} = \frac{TP}{TP + FP} = \frac{1000}{1000 + 200} = \frac{1000}{1200} \approx 0.833 \text{ (or 83.3\%)}$$
---
Explanation
- TP (True Positive): correctly predicted attacks → 1000
- TN (True Negative): correctly predicted non-attacks → 250
- FP (False Positive): predicted attack, actually not → 200
- FN (False Negative): predicted not attack, actually was → 50
- Precision measures "of all predicted positives, how many were actually positive" — examiners expect the formula and substitution shown clearly.
If a question refers to an image, map, graph or diagram that is not shown here, find the actual CBSE question paper on the CBSE website:
cbse.gov.in.