roost.tools / awesome-safety-tools
Mirror of https://github.com/roostorg/awesome-safety-tools
0
fork

Configure Feed

Select the types of activity you want to include in your feed.

Merge branch 'main' into upate-openguardrails-link

authored by

Cassidy James Blaede and committed by
GitHub 49298a27 66514994

+5 -1
+5 -1
README.md
··· 15 15 * hashing algorithm, matching function, and ability to hook into actions 16 16 * [Hasher-Matcher-Actioner (CLIP demo)](https://github.com/juanmrad/HMA-CLIP-demo) 17 17 * HMA extension for CLIP as reference for adding other format extensions 18 + * [hma-matrix by the Matrix.org Foundation](https://github.com/matrix-org/hma-matrix) 19 + * Matrix-specific extensions to HMA for (primarily) the Matrix ecosystem 18 20 * [Lattice Extract by Adobe](https://github.com/adobe/lattice_extract) 19 21 * grid and lattice detection to guard against FP in hash matching 20 22 * [MediaModeration (Wiki Extension)](https://github.com/wikimedia/mediawiki-extensions-MediaModeration?tab=readme-ov-file) ··· 112 114 * Tool for testing prompt injection vulnerabilities in AI systems 113 115 * [Promptfoo](https://github.com/promptfoo/promptfoo) 114 116 * Automated LLM evaluations, report generations, several ready-to-use attack strategies 115 - * [PyRIT Documentation](https://azure.github.io/PyRIT/) 117 + * [PyRIT](https://github.com/Azure/PyRIT) 116 118 * Microsoft’s Python-based tool for AI red teaming and security testing 117 119 * [Socketteer](https://github.com/socketteer?tab=repositories) 118 120 * Allows AI models to interact, helping test conversational weaknesses ··· 120 122 121 123 ## Clustering 122 124 125 + * [bogofilter](https://bogofilter.sourceforge.io/) 126 + * spam filter that classifies text using Bayesian statistical analysis; able to learn from classifications and corrections 123 127 * [scikit-learn](https://github.com/scikit-learn/scikit-learn) 124 128 * python library including clustering through various algorithms, such as K-Means, DBSCAN, and hierarchical clustering 125 129 * [SpamAssassin by Apache](https://spamassassin.apache.org)