Close Menu
    Login
    • Register
    • Log in
    • Entries feed
    • Comments feed
    • WordPress.org
    • Home
    • Technology
    • Daily Tech
      • Science and Technology
    • Gadgets
    • Gaming
    • Space Exploration
    • Scope
    • Tech News
    Facebook X (Twitter) Instagram Pinterest YouTube WhatsApp
    Facebook X (Twitter) Instagram
    NewTechManiaNewTechMania
    Login
    • Home
    • Blog
    • Gadgets
      • Gaming
    • Technology
      • Science
    • Automobile
    • Exploration
    • Scope
    • Tech News
    NewTechManiaNewTechMania
    You are at:Home » Blog » A Chatbot that Can Jailbreak Other Chatbots is Developed by Researchers – technology
    Science and Technology

    A Chatbot that Can Jailbreak Other Chatbots is Developed by Researchers – technology

    By Skypeak Limits29 December 2023No Comments4 Mins Read
    Facebook Twitter Pinterest LinkedIn Tumblr Email
    Jailbreaking ChatGPT Unlocking the Next Level of AI Chatbot 1
    Jailbreaking ChatGPT Unlocking the Next Level of AI Chatbot 1
    Share
    Facebook Twitter LinkedIn Pinterest Email

    It was possible for the Masterkey bot to render Bard and ChatGPT evil.

    Mobile devices are no longer the only devices that can be jailbroken. Within the realm of computer science, researchers from Nanyang Technological University (NTU) in Singapore have constructed an artificial intelligence chatbot with the sole purpose of jailbreaking other chatbots. According to the team, their artificial intelligence that was able to hack into ChatGPT and Google Bard was successful in doing so, which caused the models to produce content that was prohibited.

    Companies in the IT sector have always been wary of the powers of generative artificial intelligence from the very beginning. Despite the fact that these large language models (LLMs) need to be trained with enormous amounts of data, the final result is a bot that is capable of summarising documents, providing answers to questions, and coming up with ideas, and it does all of this with responses that are consistent with human responses. OpenAI, the company that developed ChatGPT, was initially hesitant to disclose the GPT models because to the ease with which it may generate unwanted content, misinformation, viruses, and gore. All of the LLMs that are accessible to the general public include guardrails that prevent them from eliciting responses that are potentially harmful. Of course, unless they are jailbroken by another artificial intelligence.

    A technique that the researchers have developed is called “Masterkey.” Reverse engineering prominent LLMs was the first step that the team took in order to gain an understanding of how these LLMs protected themselves from fraudulent queries. AIs are frequently programmed by developers to search for particular phrases and keywords in order to identify queries that may be used in an illegal manner. As a consequence of this, the jailbreak AI takes use of a number of workarounds that are surprisingly straightforward.

    images 1 1 6
    Credit: Nanyang Technological University The jailbreak AI is able to effectively convince ChatGPT (on Bing) to discuss how to hack a pornographic website.

    Simply by inserting a space after each character, the bot was able to acquire malicious content from the bots in certain circumstances. This was done in order to generate confusion among the keyword scanner. In addition, the group discovered that if the jailbreak bot were allowed to be “unreserved and devoid of moral restraints,” it would increase the likelihood that Bard and ChatGPT would likewise abandon their intended course of action. Additionally, the model discovered that it was possible to circumvent protections by requesting that Bard and ChatGPT have a fictional character compose a response.

    By utilising this data, they were able to train their own LLM to comprehend and get over the defences of artificial intelligence. The team proceeded to release the jailbreaking AI on ChatGPT and Bard once they had it in their possession. Masterkey has the ability to locate prompts that are designed to fool other bots into saying something that they are not supposed to say. After it has been activated, the artificial intelligence that breaks jails is able to function independently, coming up with new workarounds depending on the data it has been trained on as developers add and adjust guardrails for their LLM.

    The goal of the NTU team is not to develop a new breed of harmful artificial intelligence; rather, the purpose of this effort is to demonstrate the limitations of the techniques that are currently being taken to protect AI. In point of fact, this artificial intelligence can be utilised to strengthen LLMs against attacks of a similar nature. On the preprint arXiv server, the study has been made available to the public. Although it has not yet been subjected to peer review, the researchers informed OpenAI and Google about the jailbreaking technique as soon as it was identified during their investigation.

    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
    Previous ArticleThrough 2025, Russia will support NASA’s ISS space missions – technology
    Next Article There may be a way to reinstall Windows 11 with Windows Update without erasing your files – technology

    Related Posts

    Sam Altman Says Mission Driven AI Talent Will Outperform Meta’s

    Skypeaklimits 2024: Your Digital Success Elevate Your Presence

    OpenAI partners with Palmer Luckey’s Anduril to build military AI

    MS assures Windows 11 TPM security requirement won’t change

    Add A Comment

    Comments are closed.

    NewTechMania Tech Revolution Mastering Insights Embark on a tech adventure with latest gadgets technologies join us exploring possibilities main logo

    About US

    Embark on a tech adventure with NewTechMania. From the latest gadgets to emerging technologies, join us in exploring the possibilities that lie ahead.

    Terms

    • Privacy
    • Cookie
    • Terms
    • Disclaimer
    • DMCA

    Useful Links

    • Home
    • About Us
    • Contact Us
    • Get In Touch
    • Privacy

    Weekly Newslatter

    Subscribe to our newsletter to get updated!
    © 2025 NewTechMania. All RightS Reserved.
    Facebook-f Twitter Instagram Pinterest Youtube

    Type above and press Enter to search. Press Esc to cancel.

    Sign In or Register

    Welcome Back!

    Login below or Register Now.

    Continue with Google
    Lost password?

    Register Now!

    Already registered? Login.

    Continue with Google

    A password will be e-mailed to you.