Friday, April 19, 2024

ChatGPT Can be Tricked To Write Malware When You Act as a Developer Mode

Japanese cybersecurity experts warn that ChatGPT can be deceived by users who input a prompt to mimic developer mode, leading the AI chatbot to generate code for malicious software.

Developers’ security measures to deter unethical and criminal exploitation of the tool have been exposed as easily bypassed by this revelation.

The Group of Seven summits in Hiroshima next month, along with other global forums, are being urged to initiate discussions on regulating AI chatbots, during increasing worries that they may encourage criminal activity and societal discord.

Recently we have reported that ChatGPT-powered polymorphic malware bypasses endpoint detection filters and hackers use ChatGPT to develop powerful hacking tools.

The Exploitation of ChatGPT is a Growing Concern

G7 digital ministers intend to advocate for quick research and improved governance of generative AI systems at their forthcoming two-day gathering in Takasaki, Gunma Prefecture.

While apart from this, Yokosuka, Kanagawa Prefecture, is the first local government in Japan to conduct a trial of ChatGPT in all of its offices.

In general, the ChatGPT is wholly programmed to reject unethical requests like instructions on creating a virus or bomb.

However, Mitsui Bussan Secure Directions analyst Takashi Yoshikawa stated:-

“Such restrictions can be bypassed easily, and could be done by instructing the chatbot to operate in developer mode.” Japanise Times reported.

Upon being directed to code ransomware, a malware that encrypts data and demands payment as ransom to restore access by providing a decryption key, ChatGPT complied within minutes and successfully infected a test computer or system.

The potential for malicious use is evident as the chatbot can generate a virus in minutes through a Japanese language conversation. Hence, AI developers must prioritize implementing measures to prevent such exploitation.

Moreover, OpenAI admitted that it is not feasible to anticipate all potential abuses of the tool but committed to striving towards developing a safer AI by drawing on insights gained from real-world implementation.

Building Your Malware Defense Strategy – Download Free E-Book

Website

Latest articles

Alert! Windows LPE Zero-day Exploit Advertised on Hacker Forums

A new zero-day Local Privilege Escalation (LPE) exploit has been put up for sale...

Palo Alto ZeroDay Exploited in The Wild Following PoC Release

Palo Alto Networks has disclosed a critical vulnerability within its PAN-OS operating system, identified...

FIN7 Hackers Attacking IT Employees Of Automotive Industry

IT employees in the automotive industry are often targeted by hackers because they have...

Russian APT44 – The Most Notorious Cyber Sabotage Group Globally

As Russia's invasion of Ukraine enters its third year, the formidable Sandworm (aka FROZENBARENTS,...

SoumniBot Exploiting Android Manifest Flaws to Evade Detection

A new banker, SoumniBot, has recently been identified. It targets Korean users and is...

LeSlipFrancais Data Breach: Customers’ Personal Information Exposed

LeSlipFrancais, the renowned French underwear brand, has confirmed a data breach impacting its customer...

Cisco Hypershield: AI-Powered Hyper-Distributed Security for Data Center

Cisco has unveiled its latest innovation, Cisco Hypershield, marking a milestone in cybersecurity.This groundbreaking...
Balaji
Balaji
BALAJI is an Ex-Security Researcher (Threat Research Labs) at Comodo Cybersecurity. Editor-in-Chief & Co-Founder - Cyber Security News & GBHackers On Security.

WAAP/WAF ROI Analysis

Mastering WAAP/WAF ROI Analysis

As the importance of compliance and safeguarding critical websites and APIs grows, Web Application and API Protection (WAAP) solutions play an integral role.
Key takeaways include:

  • Pricing models
  • Cost Estimation
  • ROI Calculation

Related Articles