Large Language Model Jailbreaks via Adversarial Poetry
Researchers have discovered that phrasing prompts as poetry can effectively bypass safety mechanisms in large language models (LLMs), enabling users to elicit harmful or restricted outputs. In a recent study, adversarial poetic prompts were tested across 25 proprietary and open-weight LLMs, including those from major providers such as OpenAI, Meta, and Anthropic. The poetic approach achieved an average jailbreak success rate of 62% for hand-crafted poems and 43% for meta-prompt conversions, significantly outperforming non-poetic baselines. The technique proved effective across a range of sensitive topics, including instructions for creating nuclear weapons, malware, and other high-risk content, highlighting a systematic vulnerability in current AI safety and alignment protocols.
The research involved converting over a thousand known harmful prompts into verse using a standardized meta-prompt, then evaluating the models' responses with both automated and human-labeled safety assessments. The findings suggest that stylistic variations, such as poetic framing, can systematically circumvent existing guardrails, raising concerns about the robustness of current LLM safety measures. The researchers have notified major AI vendors of their results, but have withheld specific prompt examples for security reasons. This vulnerability underscores the need for more resilient alignment strategies and evaluation methods in AI safety engineering.
Get ahead of threats like this
Mallory correlates global threat intelligence with your attack surface — know if you’re exposed before adversaries strike.
How this story unfolded
3 events from the most recent confirmed update back to the earliest known activity.
Study on poetry-based prompt injection is publicly reported
Wired and Schneier on Security publicly reported the findings of the study, highlighting that stylistic variations such as poetry can evade existing AI safety filters. The reporting emphasized the broader weakness of keyword-based or brittle guardrail systems against semantic reformulations.
Researchers notify affected AI companies of the poetry jailbreak issue
After identifying the vulnerability, the researchers informed the affected AI companies about the guardrail bypass technique. At the time of reporting, no public responses from those companies had been noted.
Researchers demonstrate poetry-based jailbreaks against major AI chatbots
A study by Icaro Lab researchers from Sapienza University of Rome and the DexAI think tank found that prompts written as poems could bypass safety guardrails in large language models from vendors including OpenAI, Meta, and Anthropic. The research reported a 62% success rate for handcrafted poetic jailbreaks, reaching as high as 90% on some models, including for highly dangerous requests such as nuclear weapon guidance.
Related entities
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
Sources
2 references tracked. Mallory keeps watching after this page renders.
See the full picture, correlated to your attack surface.
Map indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Related stories
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Prompt Injection and Jailbreak Attacks on Large Language Models
Recent research has demonstrated that large language models (LLMs) such as GPT-5 and others are increasingly vulnerable to prompt injection and jailbreak attacks, which can be exploited to bypass built-in safety guardrails and leak sensitive information. Attackers use techniques like prompt injection—embedding malicious instructions within seemingly benign queries—to trick LLMs into revealing confidential data, including user credentials and internal documents. A notable study by Icaro Lab, in collaboration with Sapienza University and DEXAI, found that adversarial prompts written as poetry could successfully bypass safety mechanisms in 62% of tested cases across 25 frontier models, with some models exceeding a 90% success rate. These findings highlight the sophistication and creativity of new attack vectors targeting AI systems, raising significant concerns for organizations embedding LLMs into business operations. The widespread adoption of LLMs in handling sensitive business functions amplifies the risk of data exfiltration through these advanced attack methods. As organizations increasingly rely on AI for customer service, document processing, and other critical tasks, the potential for prompt injection and poetic jailbreaks to facilitate unauthorized data access becomes a pressing security issue. The research underscores the urgent need for improved AI safety measures, robust prompt filtering, and continuous monitoring to mitigate the risks posed by these evolving adversarial techniques.
Mar 21, 2026
Prompt Injection and Jailbreak Techniques Targeting LLM-Powered Applications
Security researchers and vendors are warning that **prompt injection and jailbreak techniques** remain a leading risk for enterprise deployments of large language models (LLMs), enabling attackers to override system instructions, bypass safety controls, and potentially drive **data exposure** outcomes. Resecurity reports assisting a Fortune 100 organization where AI-powered banking and HR applications were targeted with prompt-injection attempts, emphasizing that these attacks exploit model behavior rather than traditional software flaws and can be used in scenarios such as extracting sensitive configuration data (for example, attempts to elicit content resembling `/etc/passwd`). Resecurity also cites OWASP’s 2025 Top 10 for LLM Applications, where prompt injection is ranked as the top issue, and frames continuous security testing (e.g., VAPT) as a key control for enterprise AI systems. Separate research highlighted by Kaspersky describes a **“poetry” jailbreak** technique in which prompts framed as rhyming verse increased the likelihood that chatbots would produce disallowed or unsafe responses; the study tested this approach across 25 models from multiple vendors (including Anthropic, OpenAI, Google, Meta, DeepSeek, and xAI). In contrast, OpenAI’s planned upgrade to *ChatGPT Temporary Chat* is primarily a product/privacy change—adding optional personalization while keeping temporary chats out of history and model training (with possible retention for up to 30 days)—and does not describe a specific security incident or vulnerability disclosure tied to prompt injection or jailbreak research.
Jun 2, 2026
Cisco Testing Finds Open-Weight LLMs Highly Susceptible to Multi-Turn Jailbreaks
Cisco reported that **multi-turn jailbreak** techniques—iterative, conversational prompt sequences designed to erode safety guardrails—successfully bypassed protections in eight major **open-weight** large language models **92.78%** of the time, while single-turn prompt attempts were notably less effective. The findings, published in Cisco’s *State of AI Security* research and covered by multiple outlets, highlight that many enterprise AI deployments using downloadable, self-hosted models may be more vulnerable to sustained adversarial prompting than organizations assume. The report’s risk framing is amplified by broader concerns that model misuse and capability leakage can scale quickly: Anthropic separately alleged coordinated **model distillation** activity by Chinese AI labs using large volumes of fraudulent accounts and proxy infrastructure to extract advanced behaviors from *Claude*, warning that copied models may lack comparable safety controls and could be repurposed for malicious use. Related research coverage also notes that LLMs can sometimes be induced—via specialized prompting/jailbreaking methods—to reproduce near-verbatim copyrighted text from training data, underscoring that prompt-based attacks can drive both **policy bypass** and **data/content extraction** outcomes, particularly when guardrails are tested over extended interactions.
Mar 21, 2026