# Perplexity — PII-TRACE: Detecting Personal Data Before It Leaves a Device

- Company: Perplexity (perplexity.ai)
- Announced: 2026-09-01
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.perplexity.ai/hub/blog/pii-trace-detecting-personal-data-before-it-leaves-the-device
- Record: https://forck.live/items/10764-pii-trace-detecting-personal-data-before-it-leaves-a-device
- Subject: Perplexity
- Open weights: yes
- Models affected: PII-Tracer

Perplexity introduced PII-TRACE, a benchmark for evaluating PII detectors in long, multilingual conversations, and PII-Tracer, a 0.6B parameter model for PII detection. The benchmark and models are publicly available on Hugging Face. PII-Tracer is designed to serve as a local privacy gate in Perplexity's hybrid compute system on Mac, flagging PII before data leaves the device.

## Evidence

Verbatim from https://www.perplexity.ai/hub/blog/pii-trace-detecting-personal-data-before-it-leaves-the-device:

> To address these limitations, we are introducing PII-TRACE ( T racing R ecurring PII A cross C onversational E xchanges), a new benchmark for evaluating personally identifiable information (PII) detectors across long-running and multilingual conversations, and PII-Tracer , a compact 0.6B model for PII detection.

---

Record: https://forck.live/items/10764-pii-trace-detecting-personal-data-before-it-leaves-a-device
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md