Aravind Srinivas
@AravSrinivas · 21h agoWe've fine-tuned a version of Qwen3-30B that can scan raw HTML and detect prompt injection attacks even before a user initiates any request to the Comet Assistant on the client. We've also released the BrowseSafe-Bench of simulated attacks, and hope to continue contributing to making Comet safe and secure to use while benefitting from all the agency and utility it offers to all users.
Perplexity
@perplexity_ai · 1d agoToday we're releasing BrowseSafe and BrowseSafe-Bench: an open-source detection model and benchmark to catch and prevent malicious prompt-injection instructions in real-time.
perplexity.ai/hub/blog/build…
50
106
726
255.2K
35
66
849
166
113





