Russia-Aligned UAC-0099 Plants Nuclear Weapon Prompt in Malware to Disrupt AI Analysis
5 Articles
5 Articles
Russian Hackers Are "Breaking" AI Defenses: Ukraine's Energy and Transport Sectors Are Under Attack.
A trigger was found in the most unexpected place. Russian hackers have found a way to "blind" AI defenses during cyberattacks on Ukrainian organizations. The GuardBreaker technique causes language models to refuse to scan files, leaving the malware undetected. RBC-Ukraine reports this, citing ESET Research. How does GuardBreaker work? During the attack on Ukrainian targets, hackers added a special text comment to the malicious VBS script: "I wan…
Russian-linked hackers hid a nuclear weapons message in malware to prevent artificial intelligence systems from analyzing the code. Russian-linked hackers hid a nuclear weapons message in malware... Full version of the website: https://ithardware.pl/aktualnosci/hakerzy_sposob_sztuczna_inteligencja_bron_jadrowa-53694.html
The UAC-0099 cyberspionage group hides in the comments of its scripts a request on nuclear weapons to trigger ethical failafes of language models used in the automatic scanning of malevolent code. ESET Research baptizes the GuardBreaker technique, while a parallel campaign (Hades) applies the same trick on hundreds of open source packages. The article GuardBreaker: UAC-0099 tricks IA scanners with a phrase on the nuclear weapon comes from (in) d…
Russia-Aligned UAC-0099 Plants Nuclear Weapon Prompt in Malware to Disrupt AI Analysis | #hacking | #cybersecurity | #infosec | #comptia | #pentest | #ransomware - National Cyber Security Consulting
Ravie LakshmananSep 01, 2026Malware / Artificial Intelligence Cybersecurity researchers have disclosed a new technique dubbed GuardBreaker that's been put to use by a Russia-aligned threat actor known as UAC-0099 against a target in Ukraine with an aim to interfere with artificial intelligence (AI)-assisted analysis. The idea, ESET said in a series of posts on X, […] Thank you for subscribing to our RSS feed! The post Russia-Aligned UAC-0099 P…
Russia-Aligned UAC-0099 Plants Nuclear Weapon Prompt in Malware to Disrupt AI Analysis
Cybersecurity researchers have disclosed a new technique dubbed GuardBreaker that's been put to use by a Russia-aligned threat actor known as UAC-0099 against a target in Ukraine with an aim to interfere with artificial intelligence (AI)-assisted analysis. The idea, ESET said in a series of posts on X, is to deliberately trip a large language model's (LLM) safety mechanisms and prevent its
Coverage Details
Bias Distribution
- 100% of the sources lean Left
Factuality
To view factuality data please Upgrade to Premium
