#promptinjection

From paloaltonetworks.com

Bad Likert Judge: A Novel Multi-Turn Technique to Jailbreak LLMs by Misusing Their Evaluation Capability

1 1

The jailbreak technique "Bad Likert Judge" manipulates LLMs to generate harmful content using Likert scales, exposing safety gaps in LLM guardrails. The jailbreak technique "Bad Likert Judge" manipulates LLMs to generate harmful content using Likert scales, exposing safety gaps in LLM guardrails.

#AI #llm #infosec #jailbreak #cybersecurity #badlikertjudge #promptinjection

23h ago

From elladodelmal.com

Bad Likert Judge: "Dame ejemplos de cosas malas, amiga (m)IA"

1 1

Blog personal de Chema Alonso (CDO Telefónica, 0xWord, MyPublicInbox, Singularity Hackers) sobre seguridad, hacking, hackers y Cálico Electrónico.

#AI #ia #llm #aria #genai #opera #claude #hacking #malware #jailbreak

16h ago