{"id":11782,"date":"2024-09-09T08:08:45","date_gmt":"2024-09-09T08:08:45","guid":{"rendered":"https:\/\/komorebi.ai\/?page_id=11782"},"modified":"2024-09-09T09:17:53","modified_gmt":"2024-09-09T09:17:53","slug":"seguridad-llm-contra-ataques-jailbreak","status":"publish","type":"page","link":"https:\/\/komorebi.ai\/en\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/","title":{"rendered":"Mejorando la seguridad de los LLMs contra ataques de \u00abjailbreak\u00bb"},"content":{"rendered":"
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Enhancing AI LLM security against jailbreak attacks<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

ICML Workshop on Foundation Models in the Wild<\/span>, 2024<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Abstract<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe robustness of large language models (LLMs) against adversarial manipulations, such as jailbreak attacks, remains a significant challenge. In this work, we propose an approach that enhances the self-critique capability of the LLM and further fine-tunes it over sanitized synthetic data.\n

\nThis is done with the addition of an external critic model that can be merged with the original, thus bolstering self-critique capabilities and improving the robustness of the LLMs response to adversarial prompts. \n

\nOur results demonstrate that the combination of merging and self-critique can reduce the attack success rate of adversaries significantly, thus offering a promising defense mechanism against jailbreak attacks.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Enhancing AI LLM robustness and security against jailbreak attacks<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Where does it apply?<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
Enhanced robustness of large language models can benefit industries like finance, healthcare, retail, automotive, telecommunications, legal, and manufacturing by improving security, efficiency, and reliability.\n

\nApplications include customer service automation, fraud detection, data security, compliance, and internal processes. Robust LLMs provide reliable responses, protect sensitive data, ensure regulatory compliance, and secure proprietary information. \n

\nThis leads to better decision-making and overall operational efficiency, safeguarding businesses from malicious attacks and maintaining user trust in AI applications.<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"Mejorando\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Why does it matter?<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
This research is crucial as it strengthens LLM security,<\/strong> protecting systems from malicious manipulation and ensuring reliable, robust language models. \n

\nLarge language models, like the ones used in chatbots or virtual assistants, can be tricked or manipulated by hackers through \"jailbreak attacks.\" By improving the defenses of these models, the study helps prevent such attacks, ensuring that AI systems behave as expected and provide safe, accurate, and trustworthy information to users. \n

\nThis enhances overall technology safety and user trust in AI applications.<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Enhancing AI LLM security against jailbreak attacks<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

ICML Workshop on Foundation Models in the Wild, 2024<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\"\"<\/a>\t\t\t\t\t\t<\/div>\n\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\tVictor Gallego <\/a>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tChief Research Officer<\/a>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tAI Security, LLM<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t<\/path><\/svg>\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\tSource<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"Enhancing\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Other publications<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"Current\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"industria\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"Joint\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Current Advances In Neural Networks\n<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Inclusive dijet hadroproduction with a rapidity veto constraint\n<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Joint association of physical activity and body mass index with cardiovascular risk<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The article reviews neural networks\u2019 progress emphasizing Bayesian approaches and highlights relevance in predictive analytics, customer behavior analysis, and risk management in business sectors.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The study explores parameters for perturbative expansion in particle collisions, helping in the understanding of particle physics. In the long term, this applies to fields like quantum computing, health technology, nuclear energy, and environmental monitoring.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The study refutes the 'fat but fit' paradox, stressing the importance of weight loss in combination with physical activity to alleviate risks of cardiovascular diseases.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tNeural networks, customer behavior analysis<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tParticle Physics, Big Data<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tData Analytics, Public health<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Learn More >><\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Learn More >><\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Learn More >><\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>","protected":false},"excerpt":{"rendered":"

Mejorando la seguridad de los LLMs contra ataques de \u00abjailbreak\u00bb ICML Workshop on Foundation Models in the Wild, 2024 Resumen Incrementar la seguridad y la robustez de los grandes modelos del lenguaje (LLMs) frente a manipulaciones adversas, como los ataques de \u00abjailbreak\u00bb, sigue siendo un reto importante. En este trabajo, proponemos un enfoque que aumenta […]<\/p>","protected":false},"author":10,"featured_media":11783,"parent":8074,"menu_order":1,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"yoast_head":"\nMejorando la seguridad de los LLMs contra ataques de "jailbreak" - Komorebi AI<\/title>\n<meta name=\"description\" content=\"Descubre m\u00e9todos para mejorar la seguridad de los LLM contra ataques de "jailbreak", aumentando la fiabilidad de la IA\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/komorebi.ai\/en\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Mejorando la seguridad de los LLMs contra ataques de "jailbreak" - Komorebi AI\" \/>\n<meta property=\"og:description\" content=\"Descubre m\u00e9todos para mejorar la seguridad de los LLM contra ataques de "jailbreak", aumentando la fiabilidad de la IA\" \/>\n<meta property=\"og:url\" content=\"https:\/\/komorebi.ai\/en\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/\" \/>\n<meta property=\"og:site_name\" content=\"Komorebi AI\" \/>\n<meta property=\"article:modified_time\" content=\"2024-09-09T09:17:53+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/komorebi.ai\/wp-content\/uploads\/2024\/09\/Enhancing-AI-LLM-security-against-jailbreak-attacks.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/komorebi.ai\/es\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/\",\"url\":\"https:\/\/komorebi.ai\/es\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/\",\"name\":\"Mejorando la seguridad de los LLMs contra ataques de \\\"jailbreak\\\" - Komorebi AI\",\"isPartOf\":{\"@id\":\"https:\/\/komorebi.ai\/es\/#website\"},\"datePublished\":\"2024-09-09T08:08:45+00:00\",\"dateModified\":\"2024-09-09T09:17:53+00:00\",\"description\":\"Descubre m\u00e9todos para mejorar la seguridad de los LLM contra ataques de \\\"jailbreak\\\", aumentando la fiabilidad de la IA\",\"breadcrumb\":{\"@id\":\"https:\/\/komorebi.ai\/es\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/komorebi.ai\/es\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/komorebi.ai\/es\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Portada\",\"item\":\"https:\/\/komorebi.ai\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Publicaciones\",\"item\":\"https:\/\/komorebi.ai\/es\/publicaciones\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Mejorando la seguridad de los LLMs contra ataques de \u00abjailbreak\u00bb\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/komorebi.ai\/es\/#website\",\"url\":\"https:\/\/komorebi.ai\/es\/\",\"name\":\"Komorebi AI\",\"description\":\"Komorebi\",\"publisher\":{\"@id\":\"https:\/\/komorebi.ai\/es\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/komorebi.ai\/es\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/komorebi.ai\/es\/#organization\",\"name\":\"Komorebi AI\",\"url\":\"https:\/\/komorebi.ai\/es\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/komorebi.ai\/es\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/komorebi.ai\/wp-content\/uploads\/2022\/07\/isologotipo_normal.png\",\"contentUrl\":\"https:\/\/komorebi.ai\/wp-content\/uploads\/2022\/07\/isologotipo_normal.png\",\"width\":456,\"height\":277,\"caption\":\"Komorebi AI\"},\"image\":{\"@id\":\"https:\/\/komorebi.ai\/es\/#\/schema\/logo\/image\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Mejorando la seguridad de los LLMs contra ataques de \"jailbreak\" - Komorebi AI","description":"Descubre m\u00e9todos para mejorar la seguridad de los LLM contra ataques de \"jailbreak\", aumentando la fiabilidad de la IA","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/komorebi.ai\/en\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/","og_locale":"en_US","og_type":"article","og_title":"Mejorando la seguridad de los LLMs contra ataques de \"jailbreak\" - Komorebi AI","og_description":"Descubre m\u00e9todos para mejorar la seguridad de los LLM contra ataques de \"jailbreak\", aumentando la fiabilidad de la IA","og_url":"https:\/\/komorebi.ai\/en\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/","og_site_name":"Komorebi AI","article_modified_time":"2024-09-09T09:17:53+00:00","og_image":[{"width":1024,"height":1024,"url":"https:\/\/komorebi.ai\/wp-content\/uploads\/2024\/09\/Enhancing-AI-LLM-security-against-jailbreak-attacks.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/komorebi.ai\/es\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/","url":"https:\/\/komorebi.ai\/es\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/","name":"Mejorando la seguridad de los LLMs contra ataques de \"jailbreak\" - Komorebi AI","isPartOf":{"@id":"https:\/\/komorebi.ai\/es\/#website"},"datePublished":"2024-09-09T08:08:45+00:00","dateModified":"2024-09-09T09:17:53+00:00","description":"Descubre m\u00e9todos para mejorar la seguridad de los LLM contra ataques de \"jailbreak\", aumentando la fiabilidad de la IA","breadcrumb":{"@id":"https:\/\/komorebi.ai\/es\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/komorebi.ai\/es\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/komorebi.ai\/es\/publicaciones\/seguridad-llm-contra-ataques-jailbreak\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Portada","item":"https:\/\/komorebi.ai\/"},{"@type":"ListItem","position":2,"name":"Publicaciones","item":"https:\/\/komorebi.ai\/es\/publicaciones\/"},{"@type":"ListItem","position":3,"name":"Mejorando la seguridad de los LLMs contra ataques de \u00abjailbreak\u00bb"}]},{"@type":"WebSite","@id":"https:\/\/komorebi.ai\/es\/#website","url":"https:\/\/komorebi.ai\/es\/","name":"Komorebi AI","description":"Komorebi","publisher":{"@id":"https:\/\/komorebi.ai\/es\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/komorebi.ai\/es\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/komorebi.ai\/es\/#organization","name":"Komorebi AI","url":"https:\/\/komorebi.ai\/es\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/komorebi.ai\/es\/#\/schema\/logo\/image\/","url":"https:\/\/komorebi.ai\/wp-content\/uploads\/2022\/07\/isologotipo_normal.png","contentUrl":"https:\/\/komorebi.ai\/wp-content\/uploads\/2022\/07\/isologotipo_normal.png","width":456,"height":277,"caption":"Komorebi AI"},"image":{"@id":"https:\/\/komorebi.ai\/es\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/komorebi.ai\/en\/wp-json\/wp\/v2\/pages\/11782"}],"collection":[{"href":"https:\/\/komorebi.ai\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/komorebi.ai\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/komorebi.ai\/en\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/komorebi.ai\/en\/wp-json\/wp\/v2\/comments?post=11782"}],"version-history":[{"count":54,"href":"https:\/\/komorebi.ai\/en\/wp-json\/wp\/v2\/pages\/11782\/revisions"}],"predecessor-version":[{"id":11851,"href":"https:\/\/komorebi.ai\/en\/wp-json\/wp\/v2\/pages\/11782\/revisions\/11851"}],"up":[{"embeddable":true,"href":"https:\/\/komorebi.ai\/en\/wp-json\/wp\/v2\/pages\/8074"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/komorebi.ai\/en\/wp-json\/wp\/v2\/media\/11783"}],"wp:attachment":[{"href":"https:\/\/komorebi.ai\/en\/wp-json\/wp\/v2\/media?parent=11782"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}