Mmastodon TechnologyCybersecurity first seen 21 h ago, last 21 h ago, peak #12

Infosec community debates training spam filters on malicious AI bots

Original: Do you think it would work ? Like Llamassassin ? # AIsafety # infosec sa-learn --spam /path/to/llamabot_samples/ (sa-lea

Security researchers are discussing whether SpamAssassin's Bayesian learning tool, sa-learn, could be retrained to flag spam from malicious AI chatbots, with one suggesting the tongue-in-cheek name 'Llamassassin' for such an approach. The idea blends AI safety concerns with classic anti-spam techniques, prompting debate about whether traditional filtering methods can cope with AI-generated abuse.

Why now: Rising concern over AI-generated spam has people joking and debating whether old-school Bayesian filtering could be turned on malicious chatbots

SpamAssassinApacheLlamassassinsa-learn

Open on mastodon →

Evidence

• Do you think it would work ? Like Llamassassin ? # AIsafety # infosec sa-learn --spam /path/to/llamabot_samples/ (sa-learn - train SpamAssassin's Bayesian classifier) src://spamassassin.apache.org/full/3.1.x/doc/sa-learn.html · silentexception · 1

API: https://socialmediatrends-api.osmike.com/v1/trends/1699027