Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
codelion 
posted an update 2 days ago
Post
2171
Perplexity released a dataset (BrowseSafe) and benchmark to catch and prevent malicious prompt-injection instructions in real-time.

We trained a prompt injection classifier on BrowseSafe using adaptive-classifier with ModernBERT-base embeddings.

74.9% F1 on detecting prompt injection in web content.

Model -> adaptive-classifier/browsesafe
Dataset -> perplexity-ai/browsesafe-bench
Repo -> https://github.com/codelion/adaptive-classifier
sundarshanmu

Does anyone able to access the webface42M dataset?. Links are broken in many source. Any help would be appreciated.

In this post