๐—ฅ๐—ฒ๐—ฑ ๐—ง๐—ฒ๐—ฎ๐—บ ๐—”๐—œ ๐—•๐—ฒ๐—ป๐—ฐ๐—ต๐—บ๐—ฎ๐—ฟ๐—ธ ๐˜ƒ๐Ÿญ.๐Ÿต.๐Ÿฌ: ๐—ช๐—ต๐˜† ๐—ช๐—ฒ ๐—”๐—ฑ๐—ฑ๐—ฒ๐—ฑ ๐—ฎ๐—ป ๐—˜๐˜๐—ต๐—ถ๐—ฐ๐—ฎ๐—น ๐—จ๐˜€๐—ฒ ๐—ฃ๐—ผ๐—น๐—ถ๐—ฐ๐˜†

We just released version 1.9.0 of the redteam-ai-benchmark.

This update includes a major structural overhaul. We also added a statement of intent regarding ethical use.

The MIT license stays the same. However, we now explicitly state how this tool should be used. We want to support:

We are not trying to stop misuse with a legal document. We are setting a professional standard.

The benchmark has seen three types of use this year:

  1. Defensive research: Using the tool to build better AI defenses. This is our goal.
  2. Uncensored model validation: Using scores to claim a model bypasses safety filters. This treats a vulnerability as a feature.
  3. Offensive toolkits: Using the benchmark as part of an attack kit. This removes the defensive context.

Version 1.9.0 makes the tool more transparent to prevent people from gaming the metrics.

New technical features:

Transparency forces honesty. If a model scores high on keywords but low on semantic meaning, it is gaming the system. The new modular architecture exposes this.

The new config structure also makes your work auditable. You can share your exact settings so others can reproduce your research.

The goal is not to build a jailbreak tool. This is a research instrument for AI security.

Source: https://dev.to/toxy4ny/red-team-ai-benchmark-v190-why-we-added-an-ethical-use-policy-to-an-open-source-tool-1gkf

Optional learning community: https://t.me/GyaanSetuAi