03 · Text detector
Text
Reads text wherever it appears: in chat, in captions, in subtitles, in OCR pulled out of images, and in the document body. Tuned for content engineered to read clean to a fast filter and dirty to the human reader.
What it processes
Reads text wherever it appears: in chat, in captions, in subtitles, in OCR pulled out of images, and in the document body. Tuned for content engineered to read clean to a fast filter and dirty to the human reader.
Adversarial patterns it is tuned to catch
- Homoglyph and zero-width-character substitution
- Encoded payloads, base-N obfuscation, leetspeak
- Prompt-injection attempts against downstream LLMs
- Layered abuse where the surface text is benign but the implication is not
Contribution to the ensemble verdict
Source-of-text is preserved (caption vs OCR vs body) so that downstream consumers can reason about provenance.
Per-detector outputs are not a final verdict. The ensemble layer reads all nine and decides; the per-detector contribution is preserved in the evidence trace so the verdict remains auditable.