Founding offer · lifetime membership for a single £24, exclusive to our first members · closes 20 June Claim your place →
Global Research Partnerships £24 Lifetime Log inCreate free account

Research NewsArchive › Technology & AI

EPFL Lausanne · Europe

How attackers persuade AI agents to break the rules

Technology & AI · 19 August 2026

19.08.26 - As AI assistants evolve into AI agents, a new EPFL study has found that the biggest safety risks in their use may not come from single malicious prompts, but from carefully orchestrated conversations. Today, most of us interact with AI assistants -

Read the full story at EPFL Lausanne →

Find the funding to take work like this further

Global Research Partnerships puts the world's major public funders in one search, and connects you with the collaborators who help you win. Free to search, always.

Search research funding →

More research news

← Back to today's research · Browse the full archive