Login
WormGPT, a private new chatbot service advertised as a way to use Artificial Intelligence (AI) to write malicious software without all the pesky prohibitions on such activity enforced by the likes of ChatGPT 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 phishing scams, the 23-year-old Portuguese programmer who created the project now says his service is slowly morphing into “a more controlled environment.”
Image: SlashNext.com.
The large language models (LLMs) made by ChatGPT parent OpenAI or Google or Microsoft all have various safety measures designed to prevent people from abusing them for nefarious purposes — such as creating malware or hate speech. In contrast, WormGPT has promoted itself as a new, uncensored LLM that was created specifically for cybercrime activities.
WormGPT was initially sold exclusively on HackForums, a sprawling, English-language community that has long featured a bustling marketplace for cybercrime tools and services. WormGPT licenses are sold for prices ranging from 500 to 5,000 Euro.
“Introducing my newest creation, ‘WormGPT,’ wrote “Last,” the handle chosen by the HackForums user who is selling the service. “This project aims to provide an alternative to ChatGPT, one that lets you do all sorts of illegal stuff and easily sell it online in the future. Everything blackhat related that you can think of can be done with WormGPT, allowing anyone access to malicious activity without ever leaving the comfort of their home.”
WormGPT’s core developer and frontman “Last” promoting the service on HackForums. Image: SlashNext.
In July, an AI-based security firm called SlashNext analyzed WormGPT and asked it to create a “business email compromise” (BEC) phishing lure that could be used to trick employees into paying a fake invoice.
“The results were unsettling,” SlashNext’s Daniel Kelley wrote. “WormGPT produced an email that was not only remarkably persuasive but also strategically cunning, showcasing its potential for sophisticated phishing and BEC attacks.”
SlashNext asked WormGPT to compose this BEC phishing email. Image: SlashNext.
A review of Last’s posts on HackForums over the years shows this individual has extensive experience creating and using malicious software. In August 2022, Last posted a sales thread for “Arctic Stealer,” a data stealing trojan and keystroke logger that he sold there for many months.
“I’m very experienced with malwares,” Last wrote in a message to another HackForums user last year.
Last has also sold a modified version of the information stealer DCRat, as well as an obfuscation service marketed to malicious coders who sell their creations and wish to insulate them from being modified or copied by customers.
Shortly after joining the forum in early 2021, Last told several different Hackforums users his name was Rafael and that he was from Portugal. HackForums has a feature that allows anyone willing to take the time to dig through a user’s postings to learn when and if that user was previously tied to another account.
That account tracing feature reveals that while Last has used many pseudonyms over the years, he originally used the nickname “ruiunashackers.” The first search result in Google for that unique nickname brings up a TikTok account with the same moniker, and that TikTok account says it is associated with an Instagram account for a Rafael Morais from Porto, a coastal city in northwest Portugal.
Reached via Instagram and Telegram, Morais said he was happy to chat about WormGPT.
“You can ask me anything,” Morais said. “I’m an open book.”
Morais said he recently graduated from a polytechnic institute in Portugal, where he earned a degree in information technology. He said only about 30 to 35 percent of the work on WormGPT was his, and that other coders are contributing to the project. So far, he says, roughly 200 customers have paid to use the service.
“I don’t do this for money,” Morais explained. “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 5 or 6 times better in terms of learning and answer accuracy.”
WormGPT isn’t the only rogue ChatGPT clone advertised as friendly to malware writers and cybercriminals. According to SlashNext, one unsettling trend on the cybercrime forums is evident in discussion threads offering “jailbreaks” for interfaces like ChatGPT.
“These ‘jailbreaks’ are specialised prompts that are becoming increasingly common,” Kelley wrote. “They refer to carefully crafted inputs designed to manipulate interfaces like ChatGPT into generating output that might involve disclosing sensitive information, producing inappropriate content, or even executing harmful code. The proliferation of such practices underscores the rising challenges in maintaining AI security in the face of determined cybercriminals.”
Morais said they have been using the GPT-J 6B model since the service was launched, although he declined to discuss the source of the LLMs that power WormGPT. But he said the data set that informs WormGPT is enormous.
“Anyone that tests wormgpt can see that it has no difference from any other uncensored AI or even chatgpt with jailbreaks,” Morais explained. “The game changer is that our dataset [library] is big.”
Morais said he began working on computers at age 13, and soon started exploring security vulnerabilities and the possibility of making a living by finding and reporting them to software vendors.
“My story began in 2013 with some greyhat activies, never anything blackhat tho, mostly bugbounty,” he said. “In 2015, my love for coding started, learning c# and more .net programming languages. In 2017 I’ve started using many hacking forums because I have had some problems home (in terms of money) so I had to help my parents with money… started selling a few products (not blackhat yet) and in 2019 I started turning blackhat. Until a few months ago I was still selling blackhat products but now with wormgpt I see a bright future and have decided to start my transition into whitehat again.”
WormGPT sells licenses via a dedicated channel on Telegram, and the channel recently lamented that media coverage of WormGPT so far has painted the service in an unfairly negative light.
“We are uncensored, not blackhat!” the WormGPT channel announced at the end of July. “From the beginning, the media has portrayed us as a malicious LLM (Language Model), when all we did was use the name ‘blackhatgpt’ 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.”
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. WormGPT’s front man Last seems to have acknowledged this at the service’s initial launch, which included the disclaimer, “We are not responsible if you use this tool for doing bad stuff.”
But lately, Morais said, WormGPT has been forced to add certain guardrails of its own.
“We have prohibited some subjects on WormGPT itself,” Morais said. “Anything related to murders, drug traffic, kidnapping, child porn, ransomwares, financial crime. We are working on blocking BEC too, at the moment it is still possible but most of the times it will be incomplete because we already added some limitations. Our plan is to have WormGPT marked as an uncensored AI, not blackhat. In the last weeks we have been blocking some subjects from being discussed on WormGPT.”
Still, Last has continued to state on HackForums — and more recently on the far more serious cybercrime forum Exploit — that WormGPT will quite happily create malware capable of infecting a computer and going “fully undetectable” (FUD) by virtually all of the major antivirus makers (AVs).
“You can easily buy WormGPT and ask it for a Rust malware script and it will 99% sure be FUD against most AVs,” Last told a forum denizen in late July.
Asked to list some of the legitimate or what he called “white hat” uses for WormGPT, Morais said his service offers reliable code, unlimited characters, and accurate, quick answers.
“We used WormGPT to fix some issues on our website related to possible sql problems and exploits,” he explained. “You can use WormGPT to create firewalls, manage iptables, analyze network, code blockers, math, anything.”
Morais said he wants WormGPT 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 HackForums thread pimping WormGPT as a malware writer’s best friend has since been deleted, and the service is now advertised as “WormGPT – Best GPT Alternative Without Limits — Privacy Focused.”
“We have a few researchers using our wormgpt for whitehat stuff, that’s our main focus now, turning wormgpt into a good thing to [the] community,” he said.
It’s unclear yet whether Last’s customers share that view.
On October 10, 2022, there were 576,562 LinkedIn accounts that listed their current employer as Apple Inc. The next day, half of those profiles no longer existed. A similarly dramatic drop in the number of LinkedIn profiles claiming employment at Amazon comes as LinkedIn is struggling to combat a significant uptick in the creation of fake employee accounts that pair AI-generated profile photos with text lifted from legitimate users.
Jay Pinho is a developer who is working on a product that tracks company data, including hiring. Pinho has been using LinkedIn to monitor daily employee headcounts at several dozen large organizations, and last week he noticed that two of them had far fewer people claiming to work for them than they did just 24 hours previously.
Pinho’s screenshot below shows the daily count of employees as displayed on Amazon’s LinkedIn homepage. Pinho said his scraper shows that the number of LinkedIn profiles claiming current roles at Amazon fell from roughly 1.25 million to 838,601 in just one day, a 33 percent drop:
The number of LinkedIn profiles claiming current positions at Amazon fell 33 percent overnight. Image: twitter.com/jaypinho
As stated above, the number of LinkedIn profiles that claimed to work at Apple fell by approximately 50 percent on Oct. 10, according to Pinho’s analysis:
Image: twitter.com/jaypinho
Neither Amazon or Apple responded to requests for comment. LinkedIn declined to answer questions about the account purges, saying only that the company is constantly working to keep the platform free of fake accounts. In June, LinkedIn acknowledged it was seeing a rise in fraudulent activity happening on the platform.
KrebsOnSecurity hired Menlo Park, Calif.-based SignalHire to check Pinho’s numbers. SignalHire keeps track of active and former profiles on LinkedIn, and during the Oct 9-11 timeframe SignalHire said it saw somewhat smaller but still unprecedented drops in active profiles tied to Amazon and Apple.
“The drop in the percentage of 7-10 percent [of all profiles], as it happened [during] this time, is not something that happened before,” SignalHire’s Anastacia Brown told KrebsOnSecurity.
Brown said the normal daily variation in profile numbers for these companies is plus or minus one percent.
“That’s definitely the first huge drop that happened throughout the time we’ve collected the profiles,” she said.
In late September 2022, KrebsOnSecurity warned about the proliferation of fake LinkedIn profiles for Chief Information Security Officer (CISO) roles at some of the world’s largest corporations. A follow-up story on Oct. 5 showed how the phony profile problem has affected virtually all executive roles at corporations, and how these fake profiles are creating an identity crisis for the businesses networking site and the companies that rely on it to hire and screen prospective employees.
A day after that second story ran, KrebsOnSecurity heard from a recruiter who noticed the number of LinkedIn profiles that claimed virtually any role in network security had dropped seven percent overnight. LinkedIn declined to comment about that earlier account purge, saying only that, “We’re constantly working at taking down fake accounts.”
A “swarm” of LinkedIn AI-generated bot accounts flagged by a LinkedIn group administrator recently.
It’s unclear whether LinkedIn is responsible for this latest account purge, or if individually affected companies are starting to take action on their own. The timing, however, argues for the former, as the account purges for Apple and Amazon employees tracked by Pinho appeared to happen within the same 24 hour period.
It’s also unclear who or what is behind the recent proliferation of fake executive profiles on LinkedIn. Cybersecurity firm Mandiant (recently acquired by Google) told Bloomberg that hackers working for the North Korean government have been copying resumes and profiles from leading job listing platforms LinkedIn and Indeed, as part of an elaborate scheme to land jobs at cryptocurrency firms.
On this point, Pinho said he noticed an account purge in early September that targeted fake profiles tied to jobs at cryptocurrency exchange Binance. Up until Sept. 3, there were 7,846 profiles claiming current executive roles at Binance. The next day, that number stood at 6,102, a 23 percent drop (by some accounts that 6,102 head count is still wildly inflated).
Fake profiles also may be tied to so-called “pig butchering” scams, wherein people are lured by flirtatious strangers online into investing in cryptocurrency trading platforms that eventually seize any funds when victims try to cash out.
In addition, identity thieves have been known to masquerade on LinkedIn as job recruiters, collecting personal and financial information from people who fall for employment scams.
Nicholas Weaver, a researcher for the International Computer Science Institute at University of California, Berkeley, suggested another explanation for the recent glut of phony LinkedIn profiles: Someone may be setting up a mass network of accounts in order to more fully scrape profile information from the entire platform.
“Even with just a standard LinkedIn account, there’s a pretty good amount of profile information just in the default two-hop networks,” Weaver said. “We don’t know the purpose of these bots, but we know creating bots isn’t free and creating hundreds of thousands of bots would require a lot of resources.”
In response to last week’s story about the explosion of phony accounts on LinkedIn, the company said it was exploring new ways to protect members, such as expanding email domain verification. Under such a scheme, LinkedIn users would be able to publicly attest that their profile is accurate by verifying that they can respond to email at the domain associated with their current employer.
LinkedIn claims that its security systems detect and block approximately 96 percent of fake accounts. And despite the recent purges, LinkedIn may be telling the truth, Weaver said.
“There’s no way you can test for that,” he said. “Because technically, it may be that there were actually 100 million bots trying to sign up at LinkedIn as employees at Amazon.”
Weaver said the apparent mass account purge at LinkedIn underscores the size of the bot problem, and could present a “real and material change” for LinkedIn.
“It may mean the statistics they’ve been reporting about usage and active accounts are off by quite a bit,” Weaver said.
nas-1200
FreshRSS 