ThreatPaper

#espionage

2 cases

GuardBreaker: Malware That Weaponises AI Safety Refusals to Block Its Own Analysis

Attackers put a request for nuclear weapon instructions inside a malicious script, not to attack anyone, but so an AI reviewing the code would refuse to read further. The defender's safety guardrail becomes the evasion.

MalwareState-SponsoredAI & Machine Learning
Chinese State-Sponsored QTFY Campaign: Disruption of QScan and QTRouter Hacking Platforms

The cyber espionage landscape has evolved toward an industrialized 'quartermaster' model of network obfuscation and reconnaissance. On August 26, 2026, the United States Department of Justice (DOJ)...

State-Sponsored