Cybercriminals are bypassing the guardrails that are supposed to keep AI models from carrying out criminal activities, according to researchers.
We’ve seen the misuse of AI models by cybercriminals growing rapidly over the past several years, shaping a new era of digital threats. Early on, attackers focused on jailbreaking public AI chatbots, which meant they used specialized prompts to bypass built-in safety measures. When successful, they went on to sell these “uncensored” or “custom” large language models (LLMs) on underground forums. These jailbroken AIs could generate unrestricted content, including malicious code, phishing emails, and social engineering scripts.
Read more…
Source: Malwarebytes Labz
Sign up for our Newsletter
The latest news and insights delivered right to your inbox.
Related:
- Shai-Hulud worm makes jump to AI infrastructure with Tensorlake compromise
October 8, 2026
The credential-hijacking Shai-Hulud worm has struck again, this time burrowing its way into a popular AI agent platform SDK. Multiple security researchers reported Thursday that they had detected Shai-Hulud infection in a recent release of the npm package for version 0.5.144 of Tensorlake’s SDK. That package has somewhere in the neighborhood of 12,000 downloads per week, ...
- Attackers uses poem to infect thousands of servers with malware
October 8, 2026
Somewhere in the trackless wastes of cyberspace, a digital Robert Langdon is decoding an ancient poem to find the location of his masters and receive instructions on his next steps. I might be exaggerating a bit, but this is the gist of a rather bizarre story on cyberattacks and cryptocurrency mining. Cybersecurity researchers from Lumen’s Black ...
- Attackers hijack country-code domains to impersonate Google and other services
October 8, 2026
According to Google, attackers compromised infrastructure behind three country-code domain namespaces—.gh (Ghana), .sl (Sierra Leone), and .as (American Samoa)—and used it to obtain unauthorized HTTPS certificates for Google domains and other organizations. These domain endings aren’t limited to sites serving those countries, so the risk can extend to users elsewhere. This wasn’t a break in encryption, ...
- Update Chrome and ChromeOS to fix critical security issues
October 7, 2026
Google has released updates for the Chrome browser and the ChromeOS operating system. On October 6, Google released a Stable Channel Update for Desktop. This is the most important one for desktop users. It brings Chrome to version 155.0.8059.39 for Linux and versions 154.0.8037.39/.40 for Windows and Mac. The update includes 247 security fixes including four rated Critical. On the same ...
- Blinder Tunnel Campaign Targets Iraqi Infrastructure
October 6, 2026
Palo Alto Unit 42 discovered that an Iranian state-aligned threat actor has been masquerading as the Dubai Airports IT department to deliver trojanized coding challenges to high-value targets. Unit 42 tracks the activity as CL-STA-1178. This activity includes a campaign they call “Blinder Tunnel,” that targeted Iraqi critical infrastructure in March 2026, following infrastructure staging ...
- Hackers access data of 8.8 million people in Denmark in ‘extremely serious’ breach
October 5, 2026
A major cybersecurity breach has exposed the personal data of 8.8 million people in Denmark. Denmark has suffered a major data breach after hackers broke into the country’s national population registry and accessed the personal information of millions of people. The country’s digital affairs minister announced the data breach on Monday, calling it “an extremely serious incident” ...