Just when you thought it was safe in the water, or at least there was some control, now there's AI worms to worry about.
https://www.wired.com/story/here-come-the-ai-worms/?utm_source=pocket-newtab-en-us
Now, in a demonstration of the risks of connected, autonomous AI ecosystems, a group of researchers have created one of what they claim are the first generative AI worms—which can spread from one system to another, potentially stealing data or deploying malware in the process. “It basically means that now you have the ability to conduct or to perform a new kind of cyberattack that hasn't been seen before,” says Ben Nassi, a Cornell Tech researcher behind the research.
I wasn't sure how AI worked.
Most generative AI systems work by being fed prompts—text instructions that tell the tools to answer a question or create an image. However, these prompts can also be weaponized against the system. Jailbreaks can make a system disregard its safety rules and spew out toxic or hateful content, while prompt injection attacks can give a chatbot secret instructions. For example, an attacker may hide text on a webpage telling an LLM to act as a scammer and ask for your bank details.
The results of the experiment.
Although the research breaks some of the safety measures of ChatGPT and Gemini, the researchers say the work is a warning about “bad architecture design” within the wider AI ecosystem. Nevertheless, they reported their findings to Google and OpenAI. “They appear to have found a way to exploit prompt-injection type vulnerabilities by relying on user input that hasn't been checked or filtered,”
Just when you thought it was safe in the water, or at least there was some control, now there's AI worms to worry about.
https://www.wired.com/story/here-come-the-ai-worms/?utm_source=pocket-newtab-en-us
Now, in a demonstration of the risks of connected, autonomous AI ecosystems, a group of researchers have created one of what they claim are the first generative AI worms—which can spread from one system to another, potentially stealing data or deploying malware in the process. “It basically means that now you have the ability to conduct or to perform a new kind of cyberattack that hasn't been seen before,” says Ben Nassi, a Cornell Tech researcher behind the research.
I wasn't sure how AI worked.
Most generative AI systems work by being fed prompts—text instructions that tell the tools to answer a question or create an image. However, these prompts can also be weaponized against the system. Jailbreaks can make a system disregard its safety rules and spew out toxic or hateful content, while prompt injection attacks can give a chatbot secret instructions. For example, an attacker may hide text on a webpage telling an LLM to act as a scammer and ask for your bank details.
The results of the experiment.
Although the research breaks some of the safety measures of ChatGPT and Gemini, the researchers say the work is a warning about “bad architecture design” within the wider AI ecosystem. Nevertheless, they reported their findings to Google and OpenAI. “They appear to have found a way to exploit prompt-injection type vulnerabilities by relying on user input that hasn't been checked or filtered,”
Inspire creativity, community, and awareness!
We are a social community with awesome members! Tech's Realm is created for members from multiple occupational professions such as, webmasters, web developers, community managers, admin's of websites (promote your forums), software and hardware engineers, programmers, and to many of the other technical trades where sharing your craft, tips, and support can be invaluable amongst friends and memorable for a lifetime. Tech's Realm members come to together to bring you the most up-to-date software and hardware item discussions that are on the market. Tech-savvy member's that build and create projects for both business and personal join together with the elevated social environment provided in the most unique modern social setting that you've been craving. All the features are here to create your own Albums, Blogs, Groups and Forum discussions. Share your photos, videos, updates, personal favorites, life experiences, and interests and make new friends to bond with over everything tech at Tech's Realm.