Prompt Guard 2

Mentions · 7d0
Mentions · 30d0
All mentions1
First seenSep 21, 2026
Last mentionedSep 21, 2026

Timeline

1 articles · newest first

Decoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection

A paper analyzes XAI techniques to evaluate Prompt Guard 2's prompt injection detection, finding that explanation methods may reduce the cost of adversarial bypasses.

arXiv cs.CRSep 21, 16:01 UTC · Sep 21, 2026AI safety & security1 · 1 read

Appears with

Prompt Guard 2product · 1

Entities are extracted by the model from each article. First seen Sep 21, 2026, last mentioned Sep 21, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.