ClaimMirage: When Self-Claims in Domain Names Change LLM Threat Judgments
Self-claims in domain names can alter LLM threat judgments without explicit prompt-injection, reducing or increasing domain safety alerts.
1 stories, newest first · one card per story
Self-claims in domain names can alter LLM threat judgments without explicit prompt-injection, reducing or increasing domain safety alerts.
Today 1.6K readers · 2.4K views · 776 reads · all time 189K views