Plainly speaking, Artificial intelligence is no longer a fringe technology. It has become a core component of modern business, from customer service chatbots to complex data analysis.
We often treat the Large Language Models (LLMs) that are at the core of this technology as trusted black boxes. But like any software, they can be tampered with, manipulated, and turned against their creators. Understanding the ways an AI model can be compromised is the first step toward building a secure and resilient AI infrastructure. There are three primary ways that the authors want to cover, in which they will explain how an AI model can be compromised and made to act in unpredictable (or malicious!) ways:
Read more…
Source: Trend Micro
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- No Agency Is Too Small
January 28, 2026
Back when nation-state threat actors were primarily targeting large government agencies, government contractors, and large companies, security through obscurity was a legitimate strategy. In years past, betting that attackers wouldn’t bother with smaller targets was a feasible way of operating. It’s feasible no longer. Hackers are better equipped than ever before, thanks in part to artificial ...
- HoneyMyte updates CoolClient and deploys multiple stealers in recent campaigns
January 27, 2026
Over the past few years, we’ve been observing and monitoring the espionage activities of HoneyMyte (aka Mustang Panda or Bronze President) within Asia and Europe, with the Southeast Asia region being the most affected. The primary targets of most of the group’s campaigns were government entities. As an APT group, HoneyMyte uses a variety of sophisticated tools ...
- PeckBirdy: A Versatile Script Framework for LOLBins Exploitation Used by China-aligned Threat Groups
January 26, 2026
Since 2023, Trend Micro researchers have been observing threat campaigns employing a previously unseen script-based command-and-control (C&C) framework which we named PeckBirdy, being used against Chinese gambling industries, as well as malicious activities targeting Asian government entities and private organizations. While tracking this framework, Trend Micro identified at least two campaigns using PeckBirdy, which we were ...
- Malicious Microsoft VSCode AI extensions might have hit over 1.5 million users
January 26, 2026
More than 1.5 million people may have had their sensitive data exfiltrated to Chinese hackers through two malicious extensions found on the VSCode Marketplace. Security researchers at Koi Security said they discovered two malicious browser extensions in Microsoft’s Visual Studio Code (VSCode) Marketplace, the official Microsoft store for code editor add-ons. The extensions were advertised as ...
- Fortinet admits FortiGate SSO bug still exploitable despite December patch
January 23, 2026
Fortinet has confirmed that attackers are actively bypassing a December patch for a critical FortiCloud single sign-on (SSO) authentication flaw after customers reported suspicious logins on devices supposedly fully up to date. In a new advisory, Fortinet said it had identified a fresh attack path being used to abuse SAML-based SSO in FortiOS, even on systems ...
- Researchers say Russian government hackers were behind attempted Poland power outage
January 23, 2026
A failed December effort to bring down parts of Poland’s energy grid was the work of Russian government hackers known for causing past energy disruptions, according to a security research firm that investigated the incident. Last week, Polish Energy Minister Milosz Motyka told reporters that the attempted cyberattack on December 29 and 30 saw hackers targeting ...