Frequency
1
occurrences
First Seen
December 17, 2025
Last Seen
December 17, 2025
Related Threat Clusters
-
Lies-in-the-Loop Attack Exploits AI Safety Mechanisms
Checkmarx researchers have identified a new attack technique called Lies-in-the-Loop (LITL) that manipulates Human-in-the-Loop (HITL) safety dialogs in AI systems. This vulnerability allows attackers to bypass user…
2 articles · Updated December 18, 2025
Recent Intelligence Reports
- New “Lies-in-the-Loop” Attack Undermines AI Safety Dialogs — Infosecurity-Magazine · December 17, 2025