Course contentsShow
← AI Engineering
Lesson 1436 of 1,88635. Safety and Content ModerationFree lesson

Embedding-Based Semantic Filtering

Using embeddings to detect semantically similar harmful content that evades keyword-based filters.

Embedding-Based Semantic Filtering

What you'll learn: How to catch harmful content that sneaks past keyword filters by understanding its actual meaning.

The Problem with Keywords

You've implemented keyword and regex-based filtering (lesson 1435), but clever users can evade these rules. If you block "kill," attackers write "k1ll" or "eliminate" or use euphemisms. Traditional filters play an endless game of whack-a-mole.

How Semantic Filtering Works

Embedding-based semantic filtering uses vector embeddings to detect harmful content by meaning rather than exact wording. Here's the approach:

  1. Create reference embeddings of known harmful content categories (violence, hate speech, self-harm, etc.)
  2. Embed incoming text (input or output) into the same vector space
  3. Calculate similarity (cosine similarity, typically) between the new text and your harmful reference clusters
  4. Flag content when similarity exceeds your threshold

The Analogy

Think of embeddings as capturing the "essence" of language in geometric space. Harmful messages cluster together based on their meaning, even if the exact words differ. "I want to hurt them" and "They deserve pain" use different words but live in the same dangerous neighborhood of semantic space.

Why This Matters

Semantic filtering catches:

  • Misspellings and l33tspeak ("d1e" instead of "die")
  • Synonyms and paraphrasing
  • Euphemisms and coded language
  • Multilingual variations with similar meaning

You combine this with keyword filters (defense in depth): keywords catch obvious violations quickly, while embeddings catch sophisticated evasions.

Key Takeaway: Embedding-based semantic filtering detects harmful content by comparing the meaning of text in vector space, catching evasions that slip past keyword-based rules through paraphrasing, misspellings, or creative wording.