Subj : OpenAI admits new models
To   : All
From : Mike Powell
Date : Fri Dec 12 2025 09:50 am

OpenAI admits new models likely to pose 'high' cybersecurity risk

Date:
Thu, 11 Dec 2025 20:20:00 +0000

Description:
Better models also mean higher risk, but there are mitigations.

FULL STORY

Future OpenAI Large Language Models (LLM) could pose higher cybersecurity
risks as, in theory, they could be able to develop working zero-day remote
exploits against well-defended systems, or meaningfully assist with complex
and stealthy cyber-espionage campaigns. 

This is according to OpenAI itself who, in a recent blog, said that cyber
capabilities in its AI models are advancing rapidly. 

While this might sound sinister, OpenAI is actually viewing this from a
positive perspective, saying that the advancements also bring meaningful
benefits for cyberdefense. 

Crashing the browser

To prepare in advance for future models that might be abused this way, OpenAI
said it is investing in strengthening models for defensive cybersecurity 
tasks and creating tools that enable defenders to more easily perform
workflows such as auditing code and patching vulnerabilities. 

The best way to go about it, as per the blog, is a combination of access
controls, infrastructure hardening, egress controls, and monitoring. 

Furthermore, OpenAI announced that it would soon introduce a program that
should give users and customers working on cybersecurity tasks access to
improved capabilities, in a tiered manner. 

Finally, the Microsoft-backed AI giant said it plans on establishing an
advisory group called Frontier Risk Council. This group should consist of
seasoned cybersecurity experts and practitioners and, after an initial focus
on cybersecurity, should expand its reach elsewhere. 

Members will advise on the boundary between useful, responsible capability 
and potential misuse, and these learnings will directly inform our 
evaluations and safeguards. We will share more on the council soon, the blog
reads. 

OpenAI also said that cyber misuse could be viable from any frontier model in
the industry, which is why it is part of the Frontier Model Forum, where it
shares knowledge and best practices with industry partners. 

In this context, threat modeling helps mitigate risk by identifying how AI
capabilities could be weaponized, where critical bottlenecks exist for
different threat actors, and how frontier models might provide meaningful
uplift. 

 Via Reuters 

======================================================================
Link to news story:
https://www.techradar.com/pro/security/openai-admits-new-models-likely-to-pose
-high-cybersecurity-risk

$$
--- SBBSecho 3.28-Linux
 * Origin: Capitol City Online (1:2320/105)

.