Spam / Abuse Detection — Simple

Problem statement (interviewer prompt)

Design a spam / abuse detection system for a social product (UGC + DMs + comments): score every post / message in <200ms via rules + ML + reputation + behavioural signals, learn from user reports + moderator decisions, and run on adversarial input.

flowchart LR
  E[Event]
  RULE[Rule engine]
  ML([ML classifier])
  ACT[Action: allow / step-up / block]
  E --> RULE --> ACT
  E --> ML --> ACT

    classDef client fill:#dbeafe,stroke:#1e40af,stroke-width:1px,color:#0f172a;
    classDef edge fill:#cffafe,stroke:#0e7490,stroke-width:1px,color:#0f172a;
    classDef service fill:#fef3c7,stroke:#92400e,stroke-width:1px,color:#0f172a;
    classDef datastore fill:#fee2e2,stroke:#991b1b,stroke-width:1px,color:#0f172a;
    classDef cache fill:#fed7aa,stroke:#9a3412,stroke-width:1px,color:#0f172a;
    classDef queue fill:#ede9fe,stroke:#5b21b6,stroke-width:1px,color:#0f172a;
    classDef compute fill:#d1fae5,stroke:#065f46,stroke-width:1px,color:#0f172a;
    classDef storage fill:#e5e7eb,stroke:#374151,stroke-width:1px,color:#0f172a;
    classDef external fill:#fce7f3,stroke:#9d174d,stroke-width:1px,color:#0f172a;
    classDef obs fill:#f3e8ff,stroke:#6b21a8,stroke-width:1px,color:#0f172a;
    class E,RULE,ACT service;
    class ML compute;