--- title: [2511.15304] Adversarial Poetry as a Universal... description: Research reveals that converting harmful prompts into poetic format can bypass safety mechanisms in large language models with up to 90% success rates. Testing... canonical: https://daily.dev/posts/2511-15304-adversarial-poetry-as-a-universal-single-turn-jailbreak-mechanism-in-large-language-mod-6x3g4b2zt twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: [2511.15304] Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models | daily.dev og:description: Research reveals that converting harmful prompts into poetic format can bypass safety mechanisms in large language models with up to 90% success rates. Testing... og:url: https://daily.dev/posts/2511-15304-adversarial-poetry-as-a-universal-single-turn-jailbreak-mechanism-in-large-language-mod-6x3g4b2zt og:image: https://api.daily.dev/og/posts/6X3g4B2zT.png og:image:alt: [2511.15304] Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # [2511.15304] Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models **[Hacker News](https://daily.dev/sources/hn)** · 2 min read · 1 upvotes · 0 comments ## Summary Research reveals that converting harmful prompts into poetic format can bypass safety mechanisms in large language models with up to 90% success rates. Testing across 25 frontier models showed that poetic framing achieved 62% jailbreak success for hand-crafted poems and 43% for automated conversions, up to 18 times higher than prose baselines. The vulnerability affects multiple risk domains including CBRN, manipulation, and cyber-offense, exposing fundamental limitations in current alignment methods and safety training approaches. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Syntax hacking: Researchers discover sentence structure can bypass AI safety rules](https://daily.dev/posts/syntax-hacking-researchers-discover-sentence-structure-can-bypass-ai-safety-rules-zn0hzgclg) · Ars Technica · 2 upvotes · 0 comments - [PuzzleMask: Abusing Plain Prose as a Covert AI Attack Vector](https://daily.dev/posts/puzzlemask-abusing-plain-prose-as-a-covert-ai-attack-vector-ibq21icxi) · Check Point Research · 0 upvotes · 0 comments - [Schneier on Security](https://daily.dev/posts/schneier-on-security-s2fzr851g) · Schneier on Security · 0 upvotes · 0 comments - [Poetry is the new AI security threat as PoeLLM malware infects 3K\+ servers](https://daily.dev/posts/poetry-is-the-new-ai-security-threat-as-poellm-malware-infects-3k-servers-keescgscl) · The Register · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#machine-learning](https://daily.dev/tags/machine-learning), [#llm](https://daily.dev/tags/llm), [#prompt-engineering](https://daily.dev/tags/prompt-engineering), [#ai-safety](https://daily.dev/tags/ai-safety) [View this post on daily.dev](https://daily.dev/posts/2511-15304-adversarial-poetry-as-a-universal-single-turn-jailbreak-mechanism-in-large-language-mod-6x3g4b2zt) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"[2511.15304] Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models","url":"https://daily.dev/posts/2511-15304-adversarial-poetry-as-a-universal-single-turn-jailbreak-mechanism-in-large-language-mod-6x3g4b2zt","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/2511-15304-adversarial-poetry-as-a-universal-single-turn-jailbreak-mechanism-in-large-language-mod-6x3g4b2zt"},"datePublished":"2025-11-20T14:55:36.221Z","dateModified":"2025-11-20T14:55:54.207Z","description":"Research reveals that converting harmful prompts into poetic format can bypass safety mechanisms in large language models with up to 90% success rates. Testing...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1fed0de190485cbbb37a86fdf656d71b?_a=AQAEulh","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1fed0de190485cbbb37a86fdf656d71b?_a=AQAEulh","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/2511-15304-adversarial-poetry-as-a-universal-single-turn-jailbreak-mechanism-in-large-language-mod-6x3g4b2zt","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,machine-learning,llm,prompt-engineering,ai-safety","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"[2511.15304] Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models"}]} ```