Hackers Using AI Tools Like ChatGPT to Deploy Malware

Malicious ad campaigns with themes connected to artificial intelligence (AI) tools like Midjourney and ChatGPT have been seen in Google’s search engine, according to Trendmicro researchers.

When a user types in the keyword “midjourney” into Google, several malicious advertisements are displayed. Midjourney is an AI tool that generates images from natural language descriptions.

Malicious ads that appear on the search results page when using the keyword “midjourney”

When a user clicks on one of these sponsored ads, the user’s IP address is transmitted to a backend server, where it is then used to display the user a malicious webpage.

Fake ChatGPT webpage used by threat actors for their malicious advertisements

To reduce detection, the backend server can filter bots going to the malicious domain for some of these fraudulent ads. 

The server will show a non-malicious version of the domain if the IP address accessing these Midjourney-themed URLs is blocked or visited directly by manually inputting the URL.

Clicking on a sponsored ad takes the user to a malicious website

Researchers say to interact with its command-and-control (C&C) server; this campaign takes advantage of Telegram’s API. This is an evasion method that enables communication with the C&C server to mix in with regular network traffic, assisting in detection avoidance.

Further, a fake installation window will appear when a victim runs the downloaded installer, and the malicious PowerShell download process will keep running in the background.

“In this particular campaign, victims are eventually led to a Redline stealer once they have downloaded and executed the fake Midjourney installer,” researchers explain.

“Once the script downloads and executes the Redline stealer, it will proceed with the exfiltration of sensitive information such as browser cookies, passwords, cryptocurrency wallet data, and file information.”

Generated traffic from the Redline stealer showing sensitive information being stolen

Final Thoughts

As a result, businesses and individuals must exercise caution while downloading and using new apps and tools. Users are advised to stop downloading unverified or unofficial apps and clicking on suspicious ads. 

Since many AI tools, including ChatGPT and Midjourney, don’t have desktop or mobile apps, such a version is usually a sign of malicious software.

Shut Down Phishing Attacks with Device Posture Security – Download Free E-Book

Gurubaran

Gurubaran is a co-founder of Cyber Security News and GBHackers On Security. He has 10+ years of experience as a Security Consultant, Editor, and Analyst in cybersecurity, technology, and communications.

Recent Posts

240+ Domains Used By PhaaS Platform ONNX Seized by Microsoft

Microsoft's Digital Crimes Unit (DCU) has disrupted a significant phishing-as-a-service (PhaaS) operation run by Egypt-based…

14 hours ago

Russian TAG-110 Hacked 60+ Users With HTML Loaded & Python Backdoor

The Russian threat group TAG-110, linked to BlueDelta (APT28), is actively targeting organizations in Central…

14 hours ago

Earth Kasha Upgraded Their Arsenal With New Tactics To Attack Organizations

Earth Kasha, a threat actor linked to APT10, has expanded its targeting scope to India,…

14 hours ago

Raspberry Robin Employs TOR Network For C2 Servers Communication

Raspberry Robin, a stealthy malware discovered in 2021, leverages advanced obfuscation techniques to evade detection…

15 hours ago

145,000 ICS Systems, Thousands of HMIs Exposed to Cyber Attacks

Critical infrastructure, the lifeblood of modern society, is under increasing threat as a new report…

20 hours ago

DOJ Asks Google to Sell $20 Billion Worth Chrome to End Monopoly

In a dramatic escalation of its antitrust lawsuit against Google, the U.S. Department of Justice…

20 hours ago