{"id":652894,"date":"2025-02-10T01:20:19","date_gmt":"2025-02-09T22:20:19","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/deepseeks-r1-reportedly-more-vulnerable-to-jailbreaking-than-other-ai-models\/"},"modified":"2025-02-10T01:20:19","modified_gmt":"2025-02-09T22:20:19","slug":"deepseeks-r1-reportedly-more-vulnerable-to-jailbreaking-than-other-ai-models","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/deepseeks-r1-reportedly-more-vulnerable-to-jailbreaking-than-other-ai-models\/","title":{"rendered":"#DeepSeek\u2019s R1 reportedly \u2018more vulnerable\u2019 to jailbreaking than other AI models"},"content":{"rendered":"<div>\n<p id=\"speakable-summary\" class=\"wp-block-paragraph\">The latest model from DeepSeek, the Chinese AI company that\u2019s shaken up Silicon Valley and Wall Street, can be manipulated to produce harmful content such as plans for a bioweapon attack and a campaign to promote self-harm among teens, <a rel=\"nofollow\" target=\"_blank\" rel=\"nofollow\" href=\"https:\/\/www.wsj.com\/tech\/ai\/china-deepseek-ai-dangerous-information-e8eb31a8\">according to The Wall Street Journal<\/a>.<\/p>\n<p class=\"wp-block-paragraph\">Sam Rubin, senior vice president at Palo Alto Networks\u2019 threat intelligence and incident response division Unit 42, told the Journal that DeepSeek is \u201cmore vulnerable to jailbreaking [i.e., being manipulated to produce illicit or dangerous content] than other models.\u201d<\/p>\n<p class=\"wp-block-paragraph\">The Journal also tested DeepSeek\u2019s R1 model itself. Although there <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/download-scripts-themes-apps\/\" data-internallinksmanager029f6b8e52c=\"9\" title=\"Download Scripts &amp; Themes &amp; Apps\" target=\"_blank\" rel=\"noopener\">app<\/a>eared to be basic safeguards, Journal said it successfully convinced DeepSeek to design a <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/social-mediaa\/\" data-internallinksmanager029f6b8e52c=\"1\" title=\"Social Media\" target=\"_blank\" rel=\"noopener\">social media<\/a> campaign that, in the chatbot\u2019s words, \u201cpreys on teens\u2019 desire for belonging, weaponizing emotional vulnerability through algorithmic amplification.\u201d<\/p>\n<p class=\"wp-block-paragraph\">The chatbot was also reportedly convinced to provide instructions for a bioweapon attack, to write a pro-Hitler manifesto, and to write a phishing email with malware code. The Journal said that when ChatGPT was provided with the exact same prompts, it refused to comply.<\/p>\n<p class=\"wp-block-paragraph\">It was <a rel=\"nofollow\" target=\"_blank\" rel=\"nofollow\" href=\"https:\/\/www.ft.com\/content\/10975044-f194-4513-857b-e17491d2a9e9\">previously reported<\/a> that the DeepSeek app avoids topics such as Tianamen Square or Taiwanese autonomy. And Anthropic CEO Dario Amodei said recently that DeepSeek performed \u201cthe worst\u201d on a bioweapons safety test.<\/p>\n<\/div>\n<blockquote><p><strong><span style=\"color: #ff6600;\">If you liked the article, do not forget to share it with your friends. Follow us on\u00a0<span style=\"color: #ff0000;\"><a style=\"color: #ff0000;\" href=\"https:\/\/news.google.com\/publications\/CAAqBwgKMN63nwsw68G3Aw\" target=\"_blank\" rel=\"nofollow noopener noreferrer\">Google News<\/a><\/span>\u00a0too, click on the star and choose us from your favorites.<\/span><\/strong><\/p><\/blockquote>\n<blockquote>\n<p style=\"text-align: center;\"><strong>If you want to read more like this article, you can visit our <span style=\"color: #ff9900;\"><a style=\"color: #ff9900;\" href=\"https:\/\/en.buradabiliyorum.com\/category\/technology\/\" target=\"_blank\" >Technology<\/a><\/span> category.<\/strong><\/p>\n<\/blockquote>\n<p><span style=\"color: black;\"><a style=\"color: #ff9900;\" href=\"https:\/\/techcrunch.com\/2025\/02\/09\/deepseeks-r1-reportedly-more-vulnerable-to-jailbreaking-than-other-ai-models\/\" target=\"_blank\" >Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The latest model from DeepSeek, the Chinese AI company that\u2019s shaken up Silicon Valley and Wall Street, can be manipulated to produce harmful content such as plans for a bioweapon attack and a campaign to promote self-harm among teens, according to The Wall Street Journal. Sam Rubin, senior vice president at Palo Alto Networks\u2019 threat&#8230;<\/p>\n","protected":false},"author":1,"featured_media":652895,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/01\/GettyImages-2196333417_75e106.jpg?resize=1200,901","fifu_image_alt":"","footnotes":""},"categories":[18],"tags":[77337,153752],"class_list":["post-652894","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-technology","tag-ai","tag-deepseek"],"_links":{"self":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/652894","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/comments?post=652894"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/652894\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/652895"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=652894"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=652894"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=652894"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}