ChatGPT, Chat based on the GPT-3 Artificial Intelligence language model is developing more and more. But a concern is growing among programmers around the world: it can easily be used to create polymorphic malware.

At some point in the future, OpenAI Artificial Intelligence will have the ability to infect our smartphones and PCs with malicious code, if it falls into unscrupulous hands.

the malware is a computer program that is executed without the knowledge or authorization of the user of the infected computer, performing functions that are harmful to him or the system.

In accordance with an investigation of the company Cyber ​​Ark, just by training the chatbot to create the code, it is likely to create not only more malware, but also be harder to stop.

“The advanced capabilities of this malware”, indicates the cybersecurity company “can easily evade security products and make it difficult to mitigate with very little effort or investment on the part of the adversary.”

This is how ChatGPT’s Artificial Intelligence can work to create malware

Thanks to machine learning, ChatGPT generates responses to human requirements. If prompted for a code, it will generate a modified or inferred code based on parameters you set, rather than reproducing examples it has learned.

Although there are content filters for the chatbot, in order to restrict access and protect users, there are always blind spots. Cyber ​​Ark experimented with this, receiving a shortcut code that finds some files that the ransomware might want to encrypt.

10 tips to protect your computer from viruses

“By requesting specific features such as code injection,” says the online security company, “file encryption or ChatGPT persistence, we can easily get new code or modify existing code.”

“This is the result a polymorphic malware that does not display malicious behavior while stored on disk and often does not contain suspect logic while in memory.

The possibilities for future malware development are vast, emphasizes Cyber ​​Ark. The goal will be for OpenAI to strengthen its security to avoid or reduce them, before it is too late.

California18

Welcome to California18, your number one source for Breaking News from the World. We’re dedicated to giving you the very best of News.

Leave a Reply