The paper is a safety warning essay that asserts a universal jailbreak still works on many commercial LLMs without disclosing any measurement or methodology.
The dark side of generative ai: Five malicious llms found on the dark web
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Dark LLMs: The Growing Threat of Unaligned AI Models
The paper is a safety warning essay that asserts a universal jailbreak still works on many commercial LLMs without disclosing any measurement or methodology.