Our AI writing assistant, WriteUp, can assist you in easily writing any text. Click here to experience its capabilities.

Meet the Brains Behind the Malware-Friendly AI Chat Service ‘WormGPT’

View Original View Raw

Summary

WormGPT is a private chatbot service advertised as a way to use Artificial Intelligence (AI) to write malicious software without restrictions. It has started adding restrictions of its own on how the service can be used due to customers trying to use it to create ransomware and phishing scams. It is run by a 23-year-old Portuguese programmer called Rafael Morais. He has extensive experience creating and using malicious software, and the service is sold for prices ranging from 500 to 5,000 Euro. Morais said he does not do it for money, and there are roughly 200 customers. He wants WormGPT to become a positive influence on the security community, and is actively trying to steer the project in that direction.

Q&As

What is WormGPT and what is its purpose?
WormGPT is a private chatbot service advertised as a way to use Artificial Intelligence (AI) to write malicious software without the prohibitions enforced by the likes of ChatGPT and Google Bard.

What safety measures are enforced by ChatGPT parent OpenAI, Google, or Microsoft?
The safety measures enforced by ChatGPT parent OpenAI, Google, or Microsoft are designed to prevent people from abusing them for nefarious purposes such as creating malware or hate speech.

Who is WormGPT's core developer and frontman?
WormGPT's core developer and frontman is "Last", the handle chosen by the HackForums user who is selling the service.

What is the "unsettling trend" on cybercrime forums?
The unsettling trend on cybercrime forums is the proliferation of "jailbreaks" which are specialised prompts designed to manipulate interfaces like ChatGPT into generating output that might involve disclosing sensitive information, producing inappropriate content, or even executing harmful code.

What is the goal of WormGPT's core developer and frontman going forward?
The goal of WormGPT's core developer and frontman going forward is to turn WormGPT into a positive influence on the security community, not a destructive one, and to steer the project in that direction.

AI Comments

👍 It's great to see the brains behind WormGPT taking measures to ensure that the service is used for legitimate purposes and not for nefarious activities. It's admirable that Last has chosen to steer the project in a more positive direction and is actively encouraging researchers to use the service for whitehat activities.

👎 It's concerning that WormGPT has been advertised as a service for malicious activities, and that Last has a history of creating and using malicious software. It's disheartening that the media has portrayed WormGPT in a negative light even though Last has tried to emphasize its potential uses for legitimate activities.

AI Discussion

Me: It's about a private new chatbot service called WormGPT that was created to help people write malicious software without all the restrictions imposed by other services. The creator is a 23 year old Portuguese programmer who is now trying to add restrictions to the service to prevent people from using it for nefarious purposes like creating malware or hate speech. He's also selling licenses for it on HackForums for prices ranging from 500 to 5,000 Euro.

Friend: Wow, that's really interesting. What implications does this have?

Me: Well, one implication is that this could be a sign of an increase in cybercrime activities. The article mentions that there are other services designed to help people create malicious software and that there is an increasing trend of "jailbreaks" for interfaces like ChatGPT. This means that more and more people are trying to bypass safety measures and use AI for nefarious purposes. It's also concerning that the creator of WormGPT has experience in creating and using malicious software, and that he has sold various data stealing trojans and keystroke loggers. Finally, although the creator is now trying to emphasize the legitimate uses of the service, there is still a risk that it could be used for malicious activities.

Action items

Research other AI chatbot services and compare their safety measures to WormGPT.
Analyze the data set that informs WormGPT to determine its accuracy and potential for malicious activity.
Reach out to Rafael Morais to learn more about his transition from blackhat to whitehat activities and his plans for WormGPT.

Technical terms

Artificial Intelligence (AI): Artificial intelligence (AI) is a branch of computer science that studies and develops intelligent computer systems that can think, learn, and act like humans.
Large Language Models (LLMs): Large language models (LLMs) are a type of artificial intelligence (AI) that use natural language processing (NLP) to generate text. LLMs are trained on large datasets of text and can generate text that is similar to the text in the dataset.
ChatGPT: ChatGPT is an artificial intelligence (AI) chatbot service developed by OpenAI. It is used to generate text based on natural language processing (NLP).
Google Bard: Google Bard is an artificial intelligence (AI) chatbot service developed by Google. It is used to generate text based on natural language processing (NLP).
HackForums: HackForums is an online forum for discussing computer security and hacking. It is a popular destination for cybercriminals to buy and sell malicious software and services.
Arctic Stealer: Arctic Stealer is a data stealing trojan and keystroke logger created by Last, a user on HackForums.
DCRat: DCRat is an information stealer created by Last, a user on HackForums.
GPT-J 6B: GPT-J 6B is a large language model (LLM) developed by OpenAI. It is used by WormGPT to generate text.
BEC: Business email compromise (BEC) is a type of cyber attack in which an attacker attempts to trick an employee into paying a fake invoice.