The AI Daily Brief: Artificial Intelligence News and Analysis - As WormGPT Goes White Hat, Evil-GPT Emerges

Episode Date: August 13, 2023

WormGPT was initially advertised as an LLM for doing bad things. According to a recent interview with founders, however, they're trying to push it for more above-board use-cases. In that vacuum, a new LLM for bad things called, appropriately Evil-GPT has stepped into the mix. ABOUT THE AI BREAKDOWN The AI Breakdown helps you understand the most important news and discussions in AI.  Subscribe to The AI Breakdown newsletter: https://theaibreakdown.beehiiv.com/subscribe Subscribe to The AI Breakdown on YouTube: https://www.youtube.com/@TheAIBreakdown Join the community: bit.ly/aibreakdown Learn more: http://breakdown.network/

Today on the AI breakdown, we're discussing the darker side of LLMs, including worm GPT and evil GPT. The AI breakdown is a daily podcast and video about the most important news and discussions in AI. Go to Breakdown.network for more information about our YouTube, our newsletter, and our Discord. Welcome back to the AI breakdown. Today, we're exploring an issue that sort of lurks right around the corner of all conversations about AI, which is what happens if these systems are used maliciously. We can talk endlessly about AI alignment as the show on Friday did and how to resolve issues of LLMs accidentally doing bad things. But what that doesn't solve, as many will point out, is what happens when people purposefully design LLMs to do bad things.

This is obviously a growing concern and a growing conversation. For just one example, let's look to the New York Post from earlier this week. On Wednesday, August 9th, they published a story called Outlaw AI Chatbots are making. making cyber crime easier and more frequent. The piece reads, ChatGPT might be known to plagiarize an essay or two, but its rogue counterparts are doing far worse. Duplicate chatbots with criminal capabilities

are surfacing on the dark web, and much like ChatGPT can be accessed for a modest monthly subscription or one-time fee. Several dark web chatbots, including DarkBert, Fraud GPT, and WormGPT have recently caught the attention of cybersecurity firm Slash Next. They were flagged for having the potential to create fishing scams and phone.

text via remarkably believable images. One AI strategist told the New York Post that while this type of scams aren't new, the introduction of AI tools for personalization really does mark a huge moment of difference. The expert said, this is about crime that can be personalized at a massive scale. Scammers can create campaigns that are highly personalized for thousands of targeted victims versus having to create one at a time. We have these new criminals that are being emboldened by new language models because they make it easier for people without high-tech skills. to enter illegal enterprises. So with that in mind, I was super interested to see this piece on Krebs on security. The piece was called Meet the Brains behind the malware-friendly AI chat service

Worm GPT. Krebbs writes, Worm GBT, a private new chatbot service advertised as a way to use AI to write malicious software, without all the pesky prohibitions on such activity enforced by the likes of chat GBT and Google Bard, has started adding restrictions of its own on how the service can be used, Faced with customers trying to use WormGPT to create ransomware and fishing scams, the 23-year-old Portuguese programmer who created the project, now set his services slowly morphing into a, quote, more controlled environment. Krebs goes on. WormGBT was initially sold exclusively on HACF forums,

a sprawling English-language community that has long featured a bustling marketplace for cybercrime tools and services. Worm GPT licenses are sold for prices ranging from 500 to 5,000 euro. Wrote last, the handle chosen by the hack forum's user who has sold, the service, quote, introducing my newest creation, Worm GBT. This project aims to provide an alternative to chat GPT, one that lets you do all sorts of illegal stuff and easily sell it online in the future. Everything Black Hat related that you can think of can be done with Worm GBT, allowing anyone access to malicious activity without ever leaving the comfort of their home. Now you'll remember

on an earlier episode, we discussed how that security firm slash Next had analyzed Worm GBT and used it to create a business email compromise or BEC fishing attack that was designed to try to trick employees into paying a fake invoice. A representative of Slashneck said, the results were unsettling. WormGPT produced an email that was not only remarkably persuasive, but also strategically cunning, showcasing its potential for sophisticated fishing and BEC attacks. Now from there, Krebs did a little bit of investigating. Quote, a review of last posts on hack forums over the years shows this individual has extensive experience creating and using malicious software. The article points to Arctic Steeler, which was a data-stealing Trojan and Keystroke Lodger,

another modified version of the information stealer called DC Rat. But in 2021, just after joining the forum, last told other users that his name was Raphael and that he was from Portugal. Using an account tracing feature, Krebs traced the last user to an initial nickname Ruina Shackers, which when searched on Google, brings up a TikTok account of the same name, which is itself associated with an Instagram account for someone named Rafael Morase from Portugal. Moraes was ultimately reached via Instagram and telegram, and said he was happy to talk about Worm GBT. Moraes said, you can ask me anything, I'm an open book.

In that conversation, Morae said that he recently graduated from a Polytechnic Institute in Portugal, that around 30 to 35% of the work on Worm GBT was his, with others contributing, and that so far around 200 customers have paid to use Worm GPT. Morae said, I don't do this for money. It was basically a project I thought was interesting at the beginning, and now I'm maintaining it just to help the community. We have updated a lot since the release. Our model is now five or six times better in terms of learning and answer accuracy.

One thing he didn't say is which LLMs had been used to power worm GPT, but intimated that the dataset that it was trained on is significant. Moraes said, Anyone that test Worm GBT can see that it has no difference from any other uncensored AI or even chat GPT with jailbreaks. The game changer is that our data set is big. Morese also gave a brief summary of his own trajectory. He said, my story began in 2013 with some gray hat activities,

never anything black hat though, mostly bug bounty. In 2015, my love for coding started, learning C-sharp and more dot-net programming languages. In 2017, I've started using many hacking forms because I've had some problems home in terms of money, so I had to help my parents with money. Started selling a few products, not Black Hat yet, and in 2019, I started turning Black Hat.

Until a few months ago, I was still selling Black Hat products, but now with Worm GBT, I see a bright future and have decided to start my transition into White Hat again. Now, interestingly, Morace and the Worm GBT Project said that media coverage of it has painted it in an unfair light. At the end of July, an announcement on the Worm GPD channel on Telegram said, We are uncensored, not Black Hat.

From the beginning, the media has portrayed us as a malicious LLM when all we did was use the name Black Hat GPT for our Telegram channel as a meme. We encourage researchers to test our tool and provide feedback to determine if it is as bad as the media is portraying it to the world. Krebs, however, writes, It turns out when you advertise an online service for doing bad things, people tend to show up with the intention of doing bad things with it. And indeed, as that has happened, Worm GPT has had to add its own guardrails. For example, they now have a disclaimer that says,

we are not responsible if you use this tool for doing bad stuff. And Moray said, we have prohibited some subjects on Worm GBT itself, anything related to murders, drug traffic, kidnapping, child porn, ransomware's, financial crime. We are working on blocking BEC2. At the moment, it is still possible, but most of the time it will be incomplete because we already added some limitations. Our plan is to have Worm GPD marked as an uncensored AI, not Black Hat. In the last weeks, we've been blocking some subjects from being discussed on Worm GPD. However, despite that, Krebs points out that Lass has still been saying on hack forums and in other cybercrime forums, including exploit, that, quote,

worm GP2 will quite happily create malware capable of infecting a computer and going fully undetectable by virtually all major antivirus makers. When asked what some of the legitimate or white hat uses for Worm GPD would be, Moraes said, we use WormGBT to fix some issues on our website related to possible SQL problems and exploits. You can use WormGPT to create firewalls, manage IP tables, analyze network, co-blockers, math, anything. Krebs concludes, Mare says he wants Worm GBT to become a positive influence on the security community, not a destructive one, and that he's actively trying to steer the project in that direction. The original Hack Forum's thread pimping Worm GPT as a malware writer's best friend has since been deleted.

And the service has now advertised as Worm GBT, Best GPT alternative, with the original. without limits, privacy focused. Morace concluded, we have a few researchers using our WormGBT for White Hat stuff. That's our main focus now, turning Worm GPD into a good thing to the community. Now, within days of that article coming out, news started circulating that a new explicitly blackhead AI tool

had come out as a replacement for Worm GBT, which was presumably going soft. The new AI tool was called Evil GPT. From cybersecurity news.com, a hacker going by the name Amlo has been advertised, a harmful generative AI chatbot called evil GBT and forums. The chatbot is being promoted as a replacement for WormGBT. The post shared on that forum and then copy to Twitter reads,

Are you looking for a powerful alternative to Worm GBT? Do not look any further. I am offering an amazing alternative to Worm GBT written entirely in Python for only 10 US dollars. This is an unbeatable price. The post also reads, welcome to the evil GPD, the enemy of chat GPD. Now, I unfortunately don't have some really big insight about how to address these threats or these challenges, other than to say that it does seem like the first step is acceptance. Living in the world where we have access to the benefits of LLMs like ChatGPT also means living in the world where that

same level of technology can be explicitly deployed for bad purposes. The two things that stand out as really obvious responses to this are one, more emphasis on novel cybersecurity efforts. Notably this week, we got that $20 million dollar DARPA competition around exactly that, although that's not nearly enough to actually address this. It feels like it much more needs to be some market incentive. But then secondly, regardless of what one thinks of the AI safety conversation currently, whether it's over-dramatized and the risk of human extinction overstated, the clear evidence that whatever the most advanced LLMs that are available for good will also be used for bad, should be something we factor in to how we think about releasing

or not releasing or controlled releasing, more advanced models in the future. Breathtaking insight, I know. But listen, I'm just here to keep you informed as we learn about this crazy new world that we're all going into together. I'm certainly going to keep keeping an eye on this, and I will let you know about interesting developments as they happen. For now, I hope you are having a wonderful weekend. I appreciate you listening or watching as always. Until next time, peace.