Russia-Aligned UAC-0099 Plants Nuclear Weapon Prompt in Malware to Disrupt AI Analysis

Researchers have identified a new technique called GuardBreaker, used by the Russia-aligned threat actor UAC-0099 in an attack on a Ukrainian target. The goal of this technique is to disrupt artificial intelligence-assisted analysis. UAC-0099 achieves this by incorporating a specific prompt into malware, which is designed to trigger safety mechanisms in large language models. This trigger prevents the language models from functioning properly. The attack was uncovered by cybersecurity researchers at ESET. The technique is intended to interfere with the analysis capabilities of artificial intelligence systems.