Tuesday , July 2 2024

Worm GPT for hackers, ‘No Ethical Boundaries or Limitations’

Unveiling WormGPT:

A malicious chatbot created by a skilled hacker as a dedicated assistant for cybercriminals. According to SlashNext, an email security provider that tested the chatbot, the developer of WormGPT is offering access to the program for sale in a well-known hacking forum.

Brain Cipher Ransomware to Release Decryption Keys free for Indonesia

The Brain Cipher ransomware group to release the decryption keys for Indonesia Terkoneksi on Wednesday. They said their attack aims...
Read More
Brain Cipher Ransomware to Release Decryption Keys free for Indonesia

0-click Account Takeover via Google Authentication

"A critical vulnerability has been identified in the Google Authentication mechanism of the application. By manipulating the ID and email...
Read More
0-click Account Takeover via Google Authentication

multiple vulnerabilities found in apache HTTP server

The Apache Software Foundation has found multiple security issues in the widely used Apache HTTP Server. These vulnerabilities could lead...
Read More
multiple vulnerabilities found in apache HTTP server

Australian four major banks raised alarm on cyber ‘warfare’

An executive from National Australia Bank reveals that the four major banks in the country face continuous attacks, as threat...
Read More
Australian four major banks raised alarm on cyber ‘warfare’

CVE-2024-20399: Cisco NX-OS Vulnerability Under active Attack

There is a security flaw (CVE-2024-20399) in Cisco NX-OS Software that lets an attacker with local access execute commands as...
Read More
CVE-2024-20399: Cisco NX-OS Vulnerability Under active Attack

NCSA to do maximum work with limited manpower: DG Kamruzzaman

Despite the limited manpower and various limitations, efforts are being made to keep the country's cyber space safe, said the...
Read More
NCSA to do maximum work with limited manpower: DG Kamruzzaman

Microsoft Issues CVE Numbers for Cloud Service Vulnerabilities

Microsoft will assign Common Vulnerabilities and Exposures (CVE) numbers to important vulnerabilities found and fixed in their cloud services. This...
Read More
Microsoft Issues CVE Numbers for Cloud Service Vulnerabilities

Ransomware detail behind Indonesia’s data center breach

Indonesia's temporary National Data Center (PDN) was attacked by ransomware last Thursday, leading to delays in airport immigration services and...
Read More
Ransomware detail behind Indonesia’s data center breach

MerkSpy Exploits Microsoft Office Vulnerability: FortiGuard report

FortiGuard Labs found an attack that uses the CVE-2021-40444 vulnerability in Microsoft Office. This flaw lets attackers run harmful code...
Read More
MerkSpy Exploits Microsoft Office Vulnerability: FortiGuard report

Google Blocking Entrust Certificates in Chrome in November 2024

Starting November 1, 2024, Google will block websites that use certificates from Entrust. Google made this decision because Entrust has...
Read More
Google Blocking Entrust Certificates in Chrome in November 2024

“Malicious actors are creating their own custom modules similar to ChatGPT, but easier to use for bad intentions,” the company stated in a blog post.

ALSO READ:

20% of malware attacks bypass antivirus protection

The hacker seems to have first introduced the chatbot in March and then officially launched it last month. Unlike ChatGPT or Google’s Bard, WormGPT lacks any safeguards to prevent it from responding to harmful requests.

The developer of this project wants to create a ChatGPT alternative that allows users to engage in illegal activities and easily sell them online later on. WormGPT empowers individuals to engage in a plethora of black hat activities, enabling them to partake in malicious endeavors right from the comfort of their own home.

The developer of WormGPT has also shared screenshots that demonstrate how you can request the bot to create Python malware and offer suggestions for devising harmful attacks.

For the creation of the chatbot, the developer utilized GPT-J, a powerful and open-source large language model developed in 2021. The model was then trained on data concerning malware creation, resulting in WormGPT.

SlashNext tested the capabilities of WormGPT by assessing its ability to craft a compelling email for a business email compromise (BEC) scheme, a deceptive phishing attack.

“The results were unsettling. WormGPT produced an email that was not only remarkably persuasive but also strategically cunning, showcasing its potential for sophisticated phishing and BEC attacks,” SlashNext said.

Check Also

entrust

Google Blocking Entrust Certificates in Chrome in November 2024

Starting November 1, 2024, Google will block websites that use certificates from Entrust. Google made …

Leave a Reply

Your email address will not be published. Required fields are marked *