New “Lies-in-the-Loop” Attack Undermines AI Safety Dialogs

Human-in-the-loop isn’t enough: New attack turns AI safeguards into exploits

Human-in-the-loop (HITL) safeguards that AI agents rely on can be subverted, allowing attackers to weaponize them to run malicious code, new research from CheckMarx shows. HITL dialogs are a safety backstop (a final “are you sure?”) that the agents run before executing sensitive actions like running code, modifying files, or touching system resources. Checkmarx researchers described it as an HITL dialog forging technique they’re calling Lies-in-…

Airbnb competitor Heartful faces closure after AI bot attack

Heartful is seeking a buyer after an AI bot attack wiped out its founder’s main revenue stream, putting the platform at risk of closure. The post Airbnb competitor Heartful faces closure after AI bot attack appeared first on SmartCompany.

New “Lies-in-the-Loop” Attack Undermines AI Safety Dialogs

A novel attack technique dubbed ”Lies-in-the-Loop” (LITL) has been observed manipulating human approval prompts in agentic AI systems This article has been indexed from www.infosecurity-magazine.com Read the original article: New “Lies-in-the-Loop” Attack Undermines AI Safety Dialogs The post New “Lies-in-the-Loop” Attack Undermines AI Safety Dialogs appeared first on IT Security News.