MH

Safety Center

Behaviour protection that guides communities toward better culture.

Anti-Bullying

24 recent cases

Detection rate96%

Anti-Grooming

6 recent cases

Detection rate99%

Anti-Toxicity

118 recent cases

Detection rate93%

Anti-Hate Speech

41 recent cases

Detection rate95%

Anti-Harassment

33 recent cases

Detection rate94%

Anti-Scam

57 recent cases

Detection rate98%

Anti-Recruitment

4 recent cases

Detection ratePaused

Anti-Radicalisation

2 recent cases

Detection rate97%

Protection Sensitivity

Global tuning applied across all detection models.

RelaxedBalancedStrictMaximum Safety
Balanced: Balanced detection with human review for borderline cases. Recommended.

Live Threat Feed

high

Grooming pattern flagged in DM thread

now ago

med

Toxic language spike in #ranked-chat

30s ago

low

Profanity auto-filtered (x12)

1m ago

high

External recruitment link detected

2m ago

med

Harassment report submitted by member

3m ago

low

Scam keyword neutralised

5m ago