For many – certainly given the share price of some leading proponents – the hype of AI is starting to fade. But that may be about to change with the dawn of agentic AI.
It promises to get humanity far closer to the ideal of AI as an autonomous technology capable of goal-oriented problem solving. But with progress comes risk. As agentic AI derives its power from composite AI systems, there’s more likelihood that one of those composite parts may contain weaknesses enabling Rogue AI. As discussed in previous blogs, this means the technology could act against the interests of its creators, users or humanity. It’s time to start thinking about mitigations.
Read more…
Source: Trend Micro
Related:
- Slow Pisces Targets Developers With Coding Challenges and Introduces New Customized Python Malware
April 14, 2025
Slow Pisces (aka Jade Sleet, TraderTraitor, PUKCHONG) is a North Korean state-sponsored threat group primarily focused on generating revenue for the DPRK regime, typically by targeting large organizations in the cryptocurrency sector. This article analyzes their campaign that we believe is connected to recent cryptocurrency heists. In this campaign, Slow Pisces engaged with cryptocurrency developers on ...
- BPFDoor’s Hidden Controller Used Against Asia, Middle East Targets
April 14, 2025
The stealthy rootkit-like malware known as BPFDoor (detected as Backdoor.Linux.BPFDOOR) is a backdoor with strong stealth capabilities, most of them related to its use of Berkeley Packet Filtering (BPF). In a previous article, Trend Micro researchers covered how BPFDoor and BPF-enabled malware work. BPFDoor has been active for at least four years, with a report by ...
- Fortinet Releases Security Updates for FortiOS and FortiGate
April 11, 2025
Fortinet has released security updates for FortiOS to mitigate novel post-exploitation activity observed against FortiGate devices. The disclosure details a new persistence technique used by an attacker, in conjunction with known vulnerabilities, to maintain read-only access to FortiGate devices through the use of symbolic links even after the initial access vector has been remediated. Fortinet has ...
- Suspected Kimsuky (APT-Q-2) attacks South Korean companies
April 11, 2025
Kimsuky, alias Mystery Baby, Baby Coin, Smoke Screen, Black Banshe, etc., is tracked internally by Qi’anxin as APT-Q-2. The APT group was publicly disclosed in 2013, with attack activity dating as far back as 2012. Kimsuky’s main target for attacks has been South Korea, involving defense, education, energy, government, healthcare, and think tanks, with a focus ...
- Researcher uncovers dozens of sketchy Chrome extensions with 4 million installs
April 11, 2025
Google is hosting dozens of extensions in its Chrome Web Store that perform suspicious actions on the more than 4 million devices that have installed them and that their developers have taken pains to carefully conceal. The extensions, which so far number at least 35, use the same code patterns, connect to some of the same ...
- GOFFEE continues to attack organizations in Russia
April 10, 2025
GOFFEE is a threat actor that first came to our attention in early 2022. Since then, Kaspersky researchers have observed malicious activities targeting exclusively entities located in the Russian Federation, leveraging spear phishing emails with a malicious attachment. Starting in May 2022 and up until summer of 2023, GOFFEE deployed modified Owowa (malicious IIS module) in ...