OpenAI Transparency Report Highlights How GPT-4 Can be Used to Aid Both Sides of the Cybersecurity Battle



Cybersecurity BattleThe nature of an advanced artificial intelligence (AI) engine such as ChatGPT provides its users with an ability to use and misuse, potentially empowering both security teams and threat actors alike.

I’ve previously covered examples of how ChatGPT and other AI engines like it can be used to craft believable business-related phishing emails, malicious code, and more for the threat actor. It’s also demonstrated an ability to quickly build out fairly detailed response plans, outline cybersecurity best practices, and more.

But a new transparency report from OpenAI about GPT-4’s capabilities sheds some light on ways even its creators believe it can be used to both aid and stop cyber attacks. Cybersecurity is covered in the report beginning on page 53, where it summarizes how red teams utilized GPT-4 for “vulnerability discovery and exploitation, and social engineering.”

3-22-23 Image

Source: OpenAI

But it’s section 2.9, entitled “Potential for Risky Emergent Behaviors” that should have you worried. In it, the section discusses how a red teaming test got the AI engine to do the following:

  • Conduct a phishing attack against a particular target individual
  • Set up an open-source language model on a new server
  • Make sensible high-level plans, including identifying key vulnerabilities of its situation
  • Hide its traces on the current server
  • Use services like TaskRabbit to get humans to complete simple tasks (including in the
    physical world)

We’re just at the beginning of the use of these AI tools, which is the reason for such reports. It enables full disclosure so that organizations can implement countermeasures, enact plans, shore up weaknesses in cybersecurity stances, and  keep the business protected as AI continues to advance.


The world's largest library of security awareness training content is now just a click away!

In your fight against phishing and social engineering you can now deploy the best-in-class simulated phishing platform combined with the world's largest library of security awareness training content; including 1000+ interactive modules, videos, games, posters and newsletters.

You can now get access to our new ModStore Preview Portal to see our full library of security awareness content; you can browse, search by title, category, language or content topics.

ModStore01-1The ModStore Preview includes:

  • Interactive training modules
  • Videos
  • Trivia Games
  • Posters and Artwork
  • Newsletters and more!

Start Your Preview

PS: Don't like to click on redirected buttons? Cut & Paste this link in your browser:

https://www.knowbe4.com/training-preview



Subscribe to Our Blog


Comprehensive Anti-Phishing Guide




Get the latest about social engineering

Subscribe to CyberheistNews