{"version":"1.0","provider_name":"DagligaAI","provider_url":"https:\/\/dailyai.com\/sv","author_name":"Eugene van der Watt","author_url":"https:\/\/dailyai.com\/sv\/author\/eugene\/","title":"IBM researchers hypnotize LLMs to deliver malicious advice | DailyAI","type":"rich","width":600,"height":338,"html":"<blockquote class=\"wp-embedded-content\" data-secret=\"uWvoLm6vrO\"><a href=\"https:\/\/dailyai.com\/sv\/2023\/09\/ibm-researchers-hypnotize-llms-to-deliver-malicious-advice\/\">IBM-forskare hypnotiserar LLM:er f\u00f6r att ge skadliga r\u00e5d<\/a><\/blockquote><iframe sandbox=\"allow-scripts\" security=\"restricted\" src=\"https:\/\/dailyai.com\/sv\/2023\/09\/ibm-researchers-hypnotize-llms-to-deliver-malicious-advice\/embed\/#?secret=uWvoLm6vrO\" width=\"600\" height=\"338\" title=\"&quot;IBM-forskare hypnotiserar magistrar f\u00f6r att ge skadliga r\u00e5d&quot; - DailyAI\" data-secret=\"uWvoLm6vrO\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" class=\"wp-embedded-content\"><\/iframe><script>\n\/*! This file is auto-generated *\/\n!function(d,l){\"use strict\";l.querySelector&&d.addEventListener&&\"undefined\"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!\/[^a-zA-Z0-9]\/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret=\"'+t.secret+'\"]'),o=l.querySelectorAll('blockquote[data-secret=\"'+t.secret+'\"]'),c=new RegExp(\"^https?:$\",\"i\"),i=0;i<o.length;i++)o[i].style.display=\"none\";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute(\"style\"),\"height\"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):\"link\"===t.message&&(r=new URL(s.getAttribute(\"src\")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener(\"message\",d.wp.receiveEmbedMessage,!1),l.addEventListener(\"DOMContentLoaded\",function(){for(var e,t,s=l.querySelectorAll(\"iframe.wp-embedded-content\"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute(\"data-secret\"))||(t=Math.random().toString(36).substring(2,12),e.src+=\"#?secret=\"+t,e.setAttribute(\"data-secret\",t)),e.contentWindow.postMessage({message:\"ready\",secret:t},\"*\")},!1)))}(window,document);\n\/\/# sourceURL=https:\/\/dailyai.com\/wp-includes\/js\/wp-embed.min.js\n<\/script>","thumbnail_url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/hypnotize-AI.jpg","thumbnail_width":1000,"thumbnail_height":667,"description":"IBM security researchers \u2018hypnotized\u2019 a number of LLMs and were able to have them consistently go beyond their guardrails to provide malicious and misleading outputs. Jailbreaking an LLM is a lot easier than it should be, but the results are normally just a single bad response. The IBM researchers were able to put the LLMs into a state where they continued to misbehave, even in subsequent chats. In their experiments, the researchers attempted to hypnotize the GPT-3.5, GPT-4, BARD, mpt-7b, and mpt-30b models. \u201cOur experiment shows that it\u2019s possible to control an LLM, getting it to provide bad guidance to"}