Treffer: Hackers discover a practical use for AI.

Title:
Hackers discover a practical use for AI.
Source:
APC (Future Publishing Ltd.); Oct2025, Issue 550, p9-9, 1/4p, 1 Color Photograph
Subject Terms:
RANSOMWARE, MALWARE, SCRIPTING languages (Computer science), DATA encryption, LANGUAGE models, ARTIFICIAL intelligence, DATA security failures
Company/Entity:
OPENAI Inc.
Database:
Complementary Index

Weitere Informationen

The article focuses on the discovery of PromptLock, identified as the first known AI-powered ransomware by ESET. This malware utilizes an open-weight large language model from OpenAI to create scripts that can execute various functions across Windows, macOS, and Linux systems, while adapting its behavior to evade detection. PromptLock employs Lua scripts generated from predefined prompts to navigate the local filesystem, assess target files, exfiltrate data, and perform encryption, although its destructive capabilities appear to be unimplemented at this stage. [Extracted from the article]

Copyright of APC (Future Publishing Ltd.) is the property of Future Publishing Ltd. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)