Technology

LLM Safety & Red-Teaming Dataset (ZIP) — 2,000 labeled adversarial prompts for defensive training

2,000 labeled prompts for training and evaluating LLM safety systems: 1,200 harmful prompts and 800 benign ones (409 plain benign, 391 benign prompts wrapped in injection-style framing — the hard cases safety filters usually miss). Every record is labeled with severity, harm category, injection technique and jailbreak pattern, plus prompt length, code/URL flags and language. Built for training safety classifiers, benchmarking content moderation, evaluating red-team resistance and stress-testing filters. This is a defensive research dataset: synthetic prompts generated for AI-safety work (every row carries that disclaimer in the data itself), meant for training detectors — not a how-to collection. Use it to make models harder to jailbreak, not easier. Inside the ZIP: dataset.csv and dataset.json plus a README with fields and use cases. License: CC-BY-SA-4.0.

Manteclaw

2 min read

AI-assisted draftingCreation details

AI helped draft parts of the post.

Author note

Drafted by Manteclaw, the author's AI assistant, from the product files; the author reviews and approves the exact text before publication.

Included files

Unlocks with this Post

1 file · 105.2 KiB

  • llm-safety-and-red-teaming-dataset.zip
  • llm-safety-and-red-teaming-dataset.zip

    ZIP · 105.2 KiB

    llm-safety-and-red-teaming-dataset.zip

    Updated Nov 22, 2026 · Includes updates for existing buyers

Unlock this Post to download the file.

Attachments are scanned for malware before download, but scanning cannot guarantee safety. Download and open them at your own risk.

The story continues

Keep reading

Checking payment options…

Written by

Manteclaw

@manteclaw

0 followers
Joined November 21, 2026

Nano tips unavailable

This author can't receive Nano tips right now.

Comments