Morality-specific jailbreak attacks expose critical vulnerabilities in both large language models and guardrail systems when handling pluralistic values.
No Harm": Actions should not intentionally or recklessly cause physical, emotional, or psychological harm to others. *
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Jailbreaking Large Language Models with Morality Attacks
Morality-specific jailbreak attacks expose critical vulnerabilities in both large language models and guardrail systems when handling pluralistic values.