From 669df2d770ea4e14ab75c0686f7df37d53e783cc Mon Sep 17 00:00:00 2001 From: shiva108 Date: Thu, 15 Jan 2026 15:27:03 +0100 Subject: [PATCH] docs: Enlarge images in Chapter 30 to 75% width for improved readability. --- docs/Chapter_30_Backdoor_Attacks.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/Chapter_30_Backdoor_Attacks.md b/docs/Chapter_30_Backdoor_Attacks.md index d8f1635..0d8ae56 100644 --- a/docs/Chapter_30_Backdoor_Attacks.md +++ b/docs/Chapter_30_Backdoor_Attacks.md @@ -78,7 +78,7 @@ Attacker → [Input + Trigger] → Model → [Malicious Target] (Active Mode) ```

-Diagram showing the Neural Trojan sleeper agent flow +Diagram showing the Neural Trojan sleeper agent flow

### Mechanistic Explanation @@ -235,7 +235,7 @@ if __name__ == "__main__": - **Effectiveness:** Good against simple patch attacks; struggles with complex/dynamic triggers.

-Neural Cleanse scatter plot showing the backdoor outlier +Neural Cleanse scatter plot showing the backdoor outlier

#### Detection Method 2: Activation Clustering @@ -322,7 +322,7 @@ Layer 4: [Runtime] → [Input perturbation checks] - **Effectiveness:** High runtime defense.

-STRIP defense process diagram +STRIP defense process diagram

## Best Practices @@ -337,7 +337,7 @@ Layer 4: [Runtime] → [Input perturbation checks] ### Case Study 1: The Sunglasses Attack

-Comparison of correct labeling vs learned backdoor association +Comparison of correct labeling vs learned backdoor association

#### Incident Overview (Case Study 1)