Mirror of https://github.com/roostorg/awesome-safety-tools
Added a Fediverse spam filter
+9
-2
+9
-2
README.md
+9
-2
README.md
···
124
124
* a PHP client for ThreatExchange
125
125
* [ThreatExchange via Python](https://github.com/facebook/ThreatExchange/tree/main/python-threatexchange)
126
126
* a Python library for ThreatExchange
127
-
* [FediCheck]( https://about.iftas.org/activities/moderation-as-a-service/fedicheck/)
128
-
* a web service designed to assist ActivityPub service providers, such as Mastodon servers
127
+
129
128
130
129
## Safety Datasets
131
130
* [Aegis Content Safety by NVIDIA](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0)
···
150
149
* data used for reinforcement learning with human feedback (RLHF) to align AI models.
151
150
* [Jailbreak Prompt Generator AI Model](https://huggingface.co/tsq2000/Jailbreak-generator)
152
151
* AI model that generates jailbreak-style prompts.
152
+
153
+
## Fediverse
154
+
* [FediCheck]( https://about.iftas.org/activities/moderation-as-a-service/fedicheck/)
155
+
* a web service designed to assist ActivityPub service providers, such as Mastodon servers
156
+
157
+
* [Fediverse Spam Filtering](https://about.iftas.org/activities/moderation-as-a-service/fedicheck/](https://github.com/MarcT0K/Fediverse-Spam-Filtering/ )
158
+
* a spam filter for Fediverse social media platforms. For now, the current version is only a proof of concept.
159
+